The desi savings story continues....

Check this out - opportune or what?

Indian household savings to be 15x in a decade

NEW DELHI: India may takeover the US in terms of households savings by 2020, touching the USD 5 trillion mark, as the growing economy would boost incomes of people, a study has said. "The household savings rate of 33.4 per cent would translate into incremental savings of USD 5 trillion over the next decade with growing incomes of Indian households," Assocham President Swati A Piramal said in a statement. Currently, the size of Indian household savings is over USD 330 billion, according to a study jointly done by Assocham and PricehWaterhouse Coopers.

 OK, even an avid proponent of breakthrough/non-linear growth curves and all like yours truly has difficulty believing some of those numbers there. The growth rate required for a 15x leap in household savings within a decade are beyond reach. By far. A 3x to 5x leap to ~ 1-1.5 trillion in 2010 USD is certainly do-able though. Sure, in nominal terms, if, say, the USD crashes by 50% or something, the figure quoted above may just about become possible. Who knows.

Which is why I say, be skeptical. It saves so much more time and trouble than otherwise. Wonder what kind of methodology the 'study' has employed here. I for one would certainly like to examine their data, assumptions and choices made.

Here's more meat directly from the Project scope....

 Indian households have traditionally preferred safety of bank deposits and government saving schemes. Less than 10 per cent of their investments are in other financial assets like shares, debenture and mutual funds, which is low as compared to some of the developed economies, Piramal said. "Given the quantum of savings, the need to mobilise savings into productive channels and the opportunity for financial intermediation, the next decade will be an opportunity of a lifetime for Indian capital markets," the study said.

Aha, eh?

Hope that interlude was useful.

Sudhir

Project presentations learnings summary.

Class,

As I write this, am done with all group presentations. Would rather pen down learnings early on before memory and other priorities take their toll.

First off, given the time and other constraints (you had less than a week between dataset-access and deliverable presentation), the output was by and large commendable. Some quick general observations:



1. Research Objective (R.O.) matters.
Recall from lectures 1, 2 & 3 my repeated exhortations that "A clear cut R.O. that starts with an action verb defined over a crisp actionable object sets the agenda for all that follows". Well that wasn't all blah-blah blah. Its effects are measurable, as I came to see.

Suppose the entire group was on board with and agreed upon a single, well-defined R.O., then planning, delegation and recombining different modules into a whole would have been much simplified. Coherence matters much in a project this complex and with coordination issues of the kind you must've faced. It was likely to visibly impact the quality of the outcome, and IMHO, it did.

2. Two broad approaches emerged - Asset First and Customer First.
One, where you define your research objective (R.O.) as "Identify the most attractive asset class." and the other, "Identify the most attractive customer segment." The two R.O.s lead to 2 very different downstream paths.

Most groups preferred the first (asset first) route. Here, the game was to ID the most attractive asset classes using size, monetary value as addressable market or some such criterion and then filter in only those respondents who showed some interest in the selected asset classes. Then characterize the indirect respondent segments obtained and build recommendations on that basis.

I was trying to nudge people towards the second, "Customer segmentation first" route partly because it aligns much more closely with the core Marketing STP (Segmentation-Targeting-Positioning) way. In this approach, the entire respondent base is first segmented along psychographic- behavioral - motivational or demographic bases, then different segments are evaluated for attractiveness based on some criterion - monetary value, count or share etc, and then the most attractive segments are profiled/analyzed for asset class preferences and investments.

Am happy to say that in a majority of the groups, once a group implicitly chose a particular R.O., the approach that followed was logically consistent with the R.O.

3. Some novel, surprising things.
Just reeling off a few quick ones that do come to my mind.

One, how do you select the "most attractive" segment or asset class given a set of options? Some groups went with a simple count criterion - count the # of respondents corresponding to that cluster and pick the largest one. Some groups went further and used a value criterion - multiply the count with (%savings times average income times % asset class allocation) to arrive at a rupee figure. This latter approach is more rigorous and objective, IMHO. There were only 2 groups that went even further in their choice of a attractiveness criterion - the customer lifetime value (CLV) criterion. They multiplied the rupee value per annum per respondent with a (cleaned up) "years to retirement" variable to obtain the revenue stream value of a respondent over his/her pre-retirement lifetime. Post-retirement, people become net consumers and not net savers, so post-retirement is a clean break from pre-retirement. I thought this last approach was simply brilliant. Wow. And even within the two groups that did use this idea, one went further and normalized cluster lifetime earnings by cluster size giving a crisp comparison benchmark.

Two, how to select the basis variables for a good clustering solution? Regardless of which approach you took, a good segmenting solution in which clusters are clear, distinct, sizeable and actionable would be required. One clear thing that emerged across multiple groups was that using only the Q27 psychographics and the Demographics wasn't yielding a good clustering solution. The very first few runs (<1 minute each on JMP and I'm told several minutes on MEXL) should have signaled that things were off with this approach. Adding more variables would have been key. Typically, groups adding savings motivation variables, Q7 constant sum etc were able to see a better clustering solution. There is seldom any ideal clustering solution and that's a valuable learning when dealing with real data (unlike the made-up data of classroom examples).

One group that stood out in the second point approach used all 113 variables in the dataset in a factor analysis -> got some 43 odd factors -> labeled and IDed them -> then selectively chose 40 from among the 43 as a segmenting basis and obtained a neat clustering solution. The reason this approach stands out in my mind 'brute force approach' is that there's no place for subjective judgment, no chance that some correlations among disparate variables will have been overlooked etc. It's also risky as such attempts are fraught with multi-collinearity and inference issues. Anyway, it seemed to have worked.

Three, when entry into real estate financial products, a regional break up that plays upon the geographic variation captured in the primary data would have been a good thing from the XYZ point of view. Would help them prioritize and better allocate resources in managerial decision making etc.

Anyway, like I have repeatedly mentioned - effort often correlates positively with learning. So I'm hoping your effort on this project did translate into enduring learning regarding research design, data work, modeling,  project planning, delegation and coordination among other things.

I wish you all the best in your future endeavors.

Goodbye and Goodluck.

Sudhir

P.S.
Would appreciate constructive feedback that may help the MKTR course next year. Many thanks to the kindred souls in Section D for the 'Thank You' card, I thought that was sweet.

For folks who have missed quizzes

Hi all,

There have been folks who have happened to miss quizzes for whatever reason. I'm writing this up to say, 'Don;t worry about it'. You won't get a zero in the quiz you've missed. We'll find some way to impute your quiz marks such that nobody - you or the rest of your section - is disadvantaged in any way.

Sudhir.

Project presentations Update

Class,

Just reviewed the first 10 presentations. I must impressive, given the time crunch and other constraints you folks were operating under.

The remaining groups which are to present, here's some updates for you.

Am told there are some evening events groups do not want to miss. At the same time, I would like this thing over for sections A and B today. Hence, this is what I propose:

If at least half a group's members can be present, then they are welcome to make their project presentation at any convenient time slot of thier choice between 2 and 9.30 pm today in my office or in the AC2 conference room (where I'm trying to arrange for a projector and computer).

The same shall go for sections C and D tomorrow as well.

Sudhir

Phase III: The way forward

Class,

The last of the traditional lectures for the last of the sections are done. The only thing remaining is the course project phase III. Some guidelines on what to expect and do:

1. In each section, the order in which groups will present will be randomly drawn. About 5, at most 6 group presentations can be accommodated in lec 10 class time itself. The other groups shall be given time slots to present between 7.30 and 9.30 pm at the AC2 LT/ MLT or NMLT on the same day as their lecture 10.

2. The time between the start of 2 consecutive presentations should be no more than 20 minutes. Ideally, budget 15 minutes for the presentation and about 3-4 minutes for Q&A. Short clarification Questions can be asked anytime during the presentation but the more long-winded questions should come only at the end. Each time will be shown a 2 minute warning sign before their 15 minutes are up.

3. The format in which the submission files are named and the content format is explained briefly in this blog post here. Kindly adhere to the same as far as possible. Use of slide animations, highlighting, multimedia etc to better make a point are welcome.

4. Only the PPTs that have been submitted prior to the blackboard dropbox deadline can be used for the presentations. We will bring the PPTs and load them a priori onto the Classroom computer. No laptop from your side would be required for the presentation.

5. Kindly ensure your entire group is present for the presentation and is reasonably up to date on and on-board with broad aspects of the project.

6. Some basic common-sensical ground rules - (i) Kindly refrain from entering or leaving the classroom when a presentation is in progress. It is needlessly distracting. Kindly use the interval between two presentations to exit/enter. (ii) Kindly feel free to ask questions from a group but no more than 1 question from 1 student/group to a presenting group.

7. Please sign and hand over the peer evaluation form to your section AAs anytime between Wednesday to Friday.

8. The evlauation criteria for Phase III include, broadly -
(A) The quality and clarity of the methodology
(B) Logical flow and consistency of Analysis
(C) Clarity of communication
(D) Handling of Q&A
(E) Quality of recommendations

Pls feel free to use whatever software works for you - MEXL, SAS, SPSS whatever.

Hope that clarifies.

Sudhir

Project related travails

Hi All,

I've been meeting groups all afternoon and evening today and some things have come up which IMHOmerit wider dissemination:

1. Have some basic roadmap in mind before you start: This is important else you risk getting lost in the data and all the analyses that are now possible. There are literally millions of ways in which a dataset that size can be sliced and diced. Groups that had no broad, big-picture idea of where they want to go with the analysis inevitably run into problems.

Now don't get me wrong, this is not to pre-judge or straitjacket your perspective or anything - the initial plan you have in mind doesn't restrict your options. It can and should be changed and improvised as the analysis proceeds.

Update: OK. Some may ask - can we get a more specific example? Here is what I had in mind when I was thinking broad, basic plan from an example I outlined in the comments section to a post below:

E.g. - First we clean data out for missing values in Qs 7,10,27 etc -> then do factor analysis on psychogr and demogr -> then did cluster analysis on the factors -> then we estimate segment sizes thus obtained -> then we look up supply side options -> arrive at recommendations.

Hope that clarifies.

2. Segmentation is the key: The Project essentially, at its core, boils down to an STP or Segmentation-Targeting-Positioning exercise. And it is the Segmentation part which is crucial to getting the TP parts right. What inputs to have for the segmentation part, what clustering bases to use, how many clusters to get out via k-means, how best to characterize those clusters and how to decide which among them is best/most attractive are, IMHO, the real tricky questions in the project.

3. Kindly ask around for JMP gyan: A good number of folk I have met seemed to have basic confusion regarding factor and cluster analyses and how to run these on JMP. This after I thought I'd done a good job going step-by-step over the procedure in class and interpreting the results. Kindly ask around for clarifications etc on the JMP implementation of these procedures. The textbook contains good overviews about the conceptual aspects of these methods.

I'm hopeful that at least a few folk in each group have a handle on these critical procedures - factor and cluster. I shall, for completeness sake, again go through them quickly tomorrow in class.

4. The 80-20 rule applies very much so in data cleaning: Chances are under 20% of the columns in the dataset will yield over 80% of its usable information content. So don't waste time cleaning data (i.e. removing missing values, nonsense answers etc) from all the columns, just the important ones only. Again, you need to have some basic plan in mind before you can ID the important columns.

Also, not all data cleaning need mean dropping rows. In some instances, missing values can perhaps be safely imputed using column means or medians or the mode (depending on data type).

Chalo, enough for now. More as updates occur.

Sudhir

Some project related Qs and clarifications

Folks,

Based on queries and comments received in class today re the project, let me try to quickly putup stuff that IMHO mertits wider dissemination.

1. Let me rush to clarify that no great detail is expected in the supply side Q.

As in, you're not expected to say - "XYZ should offer an FD [fixed deposit] with a two year minimum lock-in offering 8.75% p.a.".

No.

Saying "XYZ should offer FDs in its product portfolio." is sufficient.

2. Make the assumption that the sample adequately represents the target population - of young, urban, upwardly mobile professionals.

3. Yes, data cleaning is a long, messy process. But it is worthwhile since once it's done, the rest of the analyses follow through very easily indeed, in seconds.

4. It helps to start with some idea or set of conjectures about a set of product classes and a set of potential target segments in mind, perhaps. One can then use statistical analyses to either confirm or disprove particular hypotheses about them.

5. There is no 'right or wrong' approach to the problem. There is however a logical, coherent and data-driven approach to making actionable recommendations versus one that is not. I'll be looking for logical errors, coherency issues, unsustainable assumptions and the like in your journey to the recommendations you make in phase III.


Hope that clarifies.

Sudhir

Phase III deliverables

Class,

Your deliverable consists of a 15 + 3 minute presentation of a 30 slide PPT (excluding appendices).

Deadline for dropbox submission of PPT is morning 0600 hrs on 10-Nov (Wednesday).

You are expected to answer two questions, primarily:
1. What products/Services should XYZ offer?
2. What customer segment should be targetted with (1)?

'Why' is a corollary to both questions above. Be prepared to make and argue your case effectively using evidence from primary and/or secondary data.

More specifically, your PPT should contain:

1. Filename (mandatory) - should be groupname_section.pptx when submitted into the dropbox on blackboard.

2. Title slide (mandatory) - project title, Group Name, member names and UIDs & MKTR section.

3.  Presentation Outline (Optional) - a Contents page that outlines your presentation along sections (e.g. methodology, Q1, Q2, recommendations, etc).

4. A Methodology Section (Mandatory) - In preferably a graph or flowchart form, lay down what analysis procedures you used in what order to answer Q2 to reach the recommendations based on Q2.

5.  A Data section (Mandatory) - explains that nature and structure of the data that were used. Be very brief but very informative - write (ii) the dimensions of the data matrices used as input to in different procedures, and (ii) the sources of data - cited sources if secondary data are used, and Question numbers in the survey questionnaire if primary data are used.

I strongly suggest using a tabular format here. Packs a lot of info into compact space. Easy to read and compare too.

6. Model Expressions (Mandatory)- Write the conceptual and/or mathematical expressions of any models used. Kindly place in the appendix section a descriptives table of the input data, a brief explanation of the X variables used, and of course, output tables along with interpretation.

7. Appendix Section (Optional): Some of the less important tables can be plugged into a separate appendix section (outside the 30 slide limit) in case you are running out of slide space. Have only the most important results tables in the main portion.

8. Recommendations (Mandatory) - crisp, clear, in simple words directed towards the client. Emphasize the usability and actionability of the recommendations.

Hope that clarifies.

Sudhir 

Tying in Course learnings with phase III

Hi all,

Update: It seems to me that Q33 - media habits w.r.t. TV channels has been lost to us. There's *NO* variation in the responses anywhere in Q33 suggesting that the Q didn't work as planned. The ranking question template in qualtrics was pointlessly complex and involved some drag and drop operation that took me a while to figure. Respondents, exhausted at the fag end of the survey, can hardly be expected to get it right.

Well, now that we are dealing with REAL data, some of our learnings will be from such unfortunate events, I guess. Basically, we have lost all usable info on the media habits question. Will likely have to rely only on psychographics mostly to design a marketing communications message for the target segment now, I guess.

Continuing my last post:

We broke our research problem down into two parts - one relating to the supply side and the other, to the demand side. The supply side essentially asks what set of products the firm should offer and the demand side complements it by asking what customers want in financial/retirement planning products. The demand and supply sides are complementary and simultaneous and must be solved iteratively to arrive at a coherent, consistent answer.

Now that we have in some sense mapped the possible set of supply side options to a manageable set of target customer segments on the demand side, the Q arises, what specific analysis methods and techniques might come in use. Pls understand there's plenty of leeway here and many different ways to peel an apple. What I'll talk about here is merely 1 possible way among many alternatives.

Clearly, Factor and Cluster analyses can easily be brought into play - to reduce the # of variables in the psychographics for instance and to explore 'natural groupings' among customers on the basis of demographics (life-cycle stage.age or employment or family size etc), psychographics (risk-return appetite), asset class preference, something else altogether or some combination of all of these. Just remember Kotler gyan about what segments should be like - measurable, actionable, reachable, distinct and all that.

What about the ANOVA and regression stuff we learned? Specific hypotheses you have - such as e.g. "People in their 20s and early 30s are markedly more risk averse than those in their late 30s and 40s", or "there is systematic association between employment type and preference for fixed income/annuities post retirement" that feed into your storyline can and should be inferred using statistical analysis.

OK, what about discrete choice models (like the Logit) that we will do in lec 9? Well, turns out that just like ANOVA and multivariate regression use the 'Analyze > Fit Model' sequence in JMP, so does Logit as well. Hallelujah. Just input a categorical Y into the Y area and see, the 'Standard least squares' method type at the top-right of the screen changes to 'logistic analysis' automatically. Logistic analyses can be used to infer whether particular categorical Ys relate systematically to some set of Xs in a statistically significant way.

For instance, I could have a hypothesis saying "Public sector bank as primary bank choice relates systematically to age (older people perefer this), employment type (govt employees prefer this) and low risk-low return seekers" or something like that.

Well, applying techniques learned in class would be good and should be done wherever opportunity arises. Using methods learned outside of class is very welcome too, just be prepared for Qs on them.

The primary learning in the project comes from phase III, IMHO. It teaches us how to do phase I better based on the mistakes made in phase II questionnaire as reflected in the actual data collected. The biggest learning IMHO is a resetting of our own pre-conceived notions of what analyzing real data is like, of what can and cannot be reliably inferred from the data we do have and so on.

Well, that's it from me.

P.S.
Am prepping lec 9. Hope is to cover Discrete choice and a bit of MDS (Multidimensional scaling) under perceptual maps. Now am unable to locate good MDS tools in JMP and might have to fallback on R for this. Now, I see little scope for MDS usage in phase III, so a demo on R shouldn't be too troublesome, hopefully, IMHO.

Sudhir

Some specific phase III gyan

Hi all,

Last year's experience tells me it's better to provide some (optional) guidance and structure than none at all, given the time and other constraints we are under. So here goes:

First, if you haven't already, then kindly first read these posts for context and continuation: General gyan on the project scope and background and Some phase I guidance.

There are broadly three research questions I can see relating (i) to a market entry decision, and subsequently (ii) to an STP or Segmentation-Targeting-Positioning decision for client firm XYZ. The first, or the zeroth question rather, is a preliminary one that must be acknowledged and gotten out of the way, first thing.

0. Is there a market out there at all?
1. If yes, what are the characteristics of this market?
2. How best to reach the attractive customer segments?

The zeroth research question implicitly asks if there exists an addressable, sizeable, profitable, sustainable market in financial services and/or products given the target population (the young, upwardly mobile, urban middle class).

Now, one may say, "well, look, there are so many firms and products in this space. Ergo, there must be a good, profitable, actionable market out there. No?" Well, likely but not necessarily. The last 2 years in particular teach us that in bubble scenarios, the herd is grossly wrong. We'll have to take this call for ourselves by ourselves. In this case though, I doubt you'll have much trouble making a case for entry versus non-entry. Hint: Broadly glance at what kind of numbers we are talking about here, at the macro-level - the equivalent of a full one-third of India's GDP, from the household sector alone, needs to find a home in some combination of asset classes, every year. Would be nice if (but is by no means mandatory that) your phase III analysis incorporate some thought, rationale and recommendation regarding the entry or non-entry for XYZ in the target space.


Now consider research Qs 1 and 2. Those simple looking research questions are actually quite involved. Q1 has two sides to it - the supply side characteristics of the market and those of the demand side. Let me label these sub-questions 1.1. and 1.2. thus:

 1.1. (Supply side) What combination of products/services/solutions in what asset classes should XYZ consider offering?

 1.2. (Demand side) What is the distribution of target population preferences over asset classes and over the attributes of financial products/services/solutions?


For the supply side, ask if there exist synergies in introducing a set of products rather than just one - in terms of competencies required, talent/skills available, scale, marketing, etc. Imaginative use and application of Secondary and Primary data would be great here. For instance, primary data can at least provide directly the (stated) distribution of current and prospective investments into broadly defined asset classes. Again, this is entirely my idea of how I would think if I were in your seat. It nowhere says I am 100% right in what I am thinking. Hence, you don't have to follow my lead here and can go with some radical, innovative and totally out-of-the-box approach of your own.

For the demand side, primary data in some measure allows us to collect data on target population preferences over financial product attributes (broadly speaking) such as risk/return, time to maturity, tax saving status, benefits sought, flexibility or liquidity at short notice, etc. This rich dataset also provides opportunities for Segmentation of the customer base, along various dimensions of interest (entirely your call what you want to go with). I would rather you try to go with what can be actionable from the client firm's viewpoint.

Once some sort of segmentation base has been decided upon, segmentation done and the segments identified, labeled, sized up and analyzed, then comes Q2 with a targetting and positioning plan for the most attractive segments identified. We've asked some basic Qs about media habits and psychographics etc to help with a rudimentary marketing plan. Essentially, you are able to go one step ahead and tell the client not just what are the most attractive customer segments in the market for so-and-so asset classes, but also how to reach them, communicate with them and sell them the product.

Now the logical Q arises, how did all that we do in class come in handy here? Aha. Good Q. I shall putup a separate post explaining and connecting some of the techniques we covered with some of the research Qs above.

OK, that is it from me for this part. I'd ideally you mull over this with your group. Again, you don't have to go with this plan outline as above but kindly ensure that you bring value to client XYZ.

I'd be happy to get some feedback, comments, queries and clarifications on Phase III thus far. Pls use the comments section below should any such arise.

Some of you may have already started playing the data. Please do. You'll find the practical difficulties associated with collating, filtering, sorting out, analyzing and interpreting real data. That, IMVHO is tremendous learning for the individual, the team and the class as a whole.

Sudhir

General gyan on the project scope and background

Hi all,

One (foreign) student asked me what the logic was behind the survey questionnaire. And it is not surprising why some may say this. Knowing where one is coming from during the design phase (of the questionnaire, in this case) helps in charting an analysis course better, perhaps. I promised to make a writeup about the logic and the story behind the questionnaire. So, this is the story, the thinking and the background to the project scope.

We live in what the Chinese would call 'interesting times'. The economic crisis that manifested as a global financial markets meltdown continues to cast its shadow not just on current employment and home values but also on longer term issues such as the ability of governments and private organizations to live upto their pension and healthcare liabilities/ obligations. Regardless of whether we choose to acknowledge it or not, the fact remains that a lot of our old assumptions and beliefs about how the world works, including the bedrock currency arrangement coded in the Bretton woods II system, may no longer hold anymore.

Sample these articles -

The end of retirement (from The Economist, June 2010)

Jobs, pensions and markets (from The Economist, Aug 2010)

This has huge implications for us ordinary people as well, even in countries like India which have (so far) been less affected by the crisis.

Unlike Indian government employees, whose retirement and lifetime pension is guaranteed by the Government of India  - which because it prints its own money is technically safe from bankruptcy and default - the rest of us cannot really say our retirement and pensions are guaranteed in any real measure. Many young people in the US for instance question why they have to pay into social security when chances are they will never get to see a penny from there by the time they retire. We are indeed in the vanguard of the generations that will have to plan for their futures in exacting detail in the backdrop of increasing uncertainty in the years to come.

That automatically brings up its own host of interesting questions - How will we do? What will do? More generally, what is the current crop of professionals in their 20s and 30s thinking and planning in this scenario? How much confidence do they have in the current set of assets and institutions to protect their savings against inflation? What are their concerns, their preferences and their constraints? How and how much does their view and their actual investment pattern depend on their age, gender, wealth, life cycle stage, nature of employment or other factors?

Mind you, this is not idle chatter - In the aggregate, Indian household savings have averaged about 32-35% of GDP annually in recent years. Unprecedented, really. And thanks to all the visionaries starting with Shri PVN Rao and onto Shri AB Vajpayee and then Shri Manmohan Singh for enabling this. Coupled with an Incremental Capital Output Ratio (ICOR) of about 4 to 1, we are essentially assured growth of about 8% p.a. in real terms for at least the next few years based on sustainable internal demand alone. The choices that our target population segment - the young upwardly mobile urban middle class - will make will be multiplied several times fold as these people tend to be opinion leaders and trend setters also. Where will this mass of money flow to - which asset classes? In what proportion? With what confidence should conditions change down the line? So many questions! The project is one attempt to bring some structure and order to this confusing mass of questions by the application of the scientific method and statistical analysis to understand this conundrum. OK, that is the big picture view of a very complex issue. You've already read the scope document, so you now also have a good handle on the actual problem XYZ corp is handling.

Now, kindly read through this post made here in full if you haven't already:

http://marketing-yogi.blogspot.com/2010/10/some-phase-i-guidance.html

This summarizes my initial views on how to tackle a question as complex as this - basically that:

(i) we limit the scope to what can be done realistically. In this case, we focus only on the big-picture, only at the broad asset class level and not go into details of asset sub-classes and particular schemes available therein. I chose to focus broadly only on Equities (including MFs, SIPs and demat equities), Fixed income plans (bonds, insurance policies that fall under this purview, certain pension and annuity plans etc), property (different types and in different types of cities)

(ii) we focus only on the distribution of asset class preferences in the target population - perhaps as functions of demographics and psychographics.

(iii) we come up with recommendations for which asset classes to go with - some sort of ranking perhaps - given the preference structure of the target population.Any secondary analysis that uses population sizes for such segments (e.g. from the Marketing Whitebook) would be a great plus, IMHO.

OK. This post is at a general, big-picture level and is long enough as-is. Shall continue with more specific guidance in subsequent posts.

Again, not all of you may find general gyan of this sort immediately useful. That is fine. Feel free to go with whatever you have in mind. However, have someone in the group look for updates on the specific guidance.

Sudhir

Some quick announcements

Hi all,

A few quick announcements.

1. The deadline for phase III is Wednesday (10-11-2010) morning 6 am. A dropbox will be created and opened on blackboard for this purpose. Your deliverable for the project will be a power-point presentation with an upper limit of 30 slides for the main presentation and no limit for auxiliary or backup slides

2. Lecture 10 will essentially be student group presentations of their project report. Kindly ensure the entire group is present in class for this purpose. Groups will be picked up at random.  Presenting groups will have 15 minutes of talk time + 3 minutes of Q&A from the class at large. My colleague, prof. Tanuka Ghoshal, who once worked with IMRB Calcutta (real MKTR experience, folks!) has kindly agreed to join the panel evaluating the presentations.

OK, a few groups, maybe 4-5 can be accommodated in class, what about the rest? SO, I'll ask the other groups to take a 20 minute appointment with me and make the presentations. Shall book a conference room/MLT for the purpose. This is to ensure all groups get a fair chance to showcase their PPts, their thinking and emphasize their recommendations to XYZ.

I'll create a google spreadsheet on view access which I will fillup as you email me your preferred slots for. I'm told that since many folks have travel plans for the next weekend, I'd rather get presentations for groups of sections A and B done on Wednesday (10-Nov) itself in the evening, and those for sections C & D on 11-Nov in the evening.

3.Pls find below the lastest update on group respondent collection status. 2951 responses in and still counting, folks! This is exciting. Even dicounting say, 10% to within ISB multiple surveys by a single respondent and another 20% to incomplete/unusable survey, we still end up with a neat 2000 odd usable responses. Wow. Great going there.

4. I've been asked to write up the logic behind the way the final questionnaire has been structured. I shall attempt to provide a write-up for my thinking when I put this together, with ample help from the AAs. A lot of this hinges on what was written in the scope document and the interpretation of which was further expanded upon in this blogpost:

http://marketing-yogi.blogspot.com/2010/10/some-phase-i-guidance.html

Kindly read the above post in full if you haven't already. It pretty much represents the tack I have tried to take in designing the phase II survey. However, you needn't feel constrained with my thought process and could feel free to use the info collected to support the story you may have had in mind a priori. I shall do this over the next few days.

Even otherwise, I plan to dig up and post useful info relating to what last year's class got right and wrong regarding their project in phase III last year. Now, there's no reason why you should repeat mistakes already made last year. Hence, I would certainly recommend that at least a few people from each group keep an eye on the blog for updates in this regard.

5. I was thinking of holding an 'open' tutorial on JMP, methods, anything project related etc over the weekend sometime. Friday is diwali, sat and sun, am told many folks are traveling home for the weekend. Well, I'll try to make this monday evening sometime for roughly an hour then.

6. You may have noticed already that the final slides putup on blackboard may have some slides that either weren't covered in a particular section or have been altered significantly since. This happens because, well, the slides are evolving as the course proceeds. I would recommend that folks download the latest set of slides uploaded at the end of the lecture for section 'D' for use later on. Of course, I try to ensure earlier sections do not lose out on important things that may have come up later on. One reason for having the blog is to be able to communicate interesting/important issues arising in one section across the entire class. LIke happened in the JMP-ANOVA case in sections A and B, sometimes, it would make sense to actually re-do a portion of the slides in the subsequent lecture.

Chalo, last but not least,

"A HaJaAr HaPpY DiWaLi To YoU AnD FaMiLy!"

Sudhir

Do believe the hype

Well, was browsing through this typical Tom Friedman column titled 'Do believe the hype' - IMHO the column is rather shallow high on anecdotes and low on evidence - when I chanced upon this beautiful example of hands-on innovation aiding our rural masses in meaningful ways. I've always been a hard proponent of the mobile revolution changing business, possibilities and ecosystems and this just comes as more sweet vindication (or selective memory, whichever way you see it).

Do Believe the Hype (By THOMAS L. FRIEDMAN in NYT)

Here’s an example of why I ask these questions. It’s a typical Indian start-up I visited in a garage in South Delhi, EKO India Financial Services. Its founders, Abhishek Sinha and his brother Abhinav, began with a small insight — that low-wage Indian migrant workers flocking to Delhi from poorer states like Bihar had no place to put their savings and no secure way to send money home to their families. India has relatively few bank branches for a country its size, so many migrants stuff money in their mattresses or send cash home through traditional “hawala,” or hand-to-hand networks.
The brothers had an idea. In every Indian neighborhood or village there’s usually a mom-and-pop kiosk that sells drinks, cigarettes, candy and a few groceries. Why not turn each one into a virtual bank? So they created a software program whereby a migrant worker in Delhi using his cellphone, and proof of identity, could open a bank account registered on his cellphone text system. Mom-and-pop shopkeepers would act as the friendly neighborhood local banker and do the same.
Then the worker in New Delhi could give a kiosk owner in his slum 1,000 rupees (about $20), the shopkeeper would record it on his phone and text receipt of the deposit to the system’s mother bank, the State Bank of India. Then the worker’s wife back in Bihar could just go to the mom-and-pop kiosk in her village, also tied into the system, and make a withdrawal using her cellphone. The shopkeeper there would give her the 1,000 rupees sent by her husband. Each shopkeeper would earn a small fee from each transaction. Besides money transfers, workers could also use the system to bank their savings.
Since opening 18 months ago, their virtual bank now has 180,000 users doing more than 7,000 transactions a day through 500 “branches” — mom-and-pop kiosks — in Delhi and 200 more in Bihar and Jharkhand, the hometowns of many maids and migrants. EKO gets a tiny commission from the Bank of India for each transaction and two months ago started to turn a small profit.

Wow. Eh? They broke even. Awesome. May hajaar more such flowers and stories bloom, some led by ISB grads, I hope. So, what was the investment that went in? Where did the idea come from? Who are these young geeks out to change India and thereby the world?

Abhishek, who was inspired by a similar program in Brazil, said the kiosk owners “are already trusted people in each community” and are already in the habit of extending credit to their poor customers: “So we said, ‘Why not leverage them?’ We are the agents of the bank, and these retailers are our subagents.” The cheapest cellphone today has enough computing power to become a digital “mattress” and digital bank for the poor.

The whole system is being run out of a little house and garage with a dozen employees, a bunch of laptops, servers and the Internet. The core idea, says Abhishek, is “to close the last mile — the gap where government services end and the consumer begins.” There is a huge business in bridging that last mile for millions of poor Indians — who, without it, can’t get proper health care, education or insurance.

Wow. By now, my admiration for this duo is sky high already. Think of what an incorruptible biometric identification universal ID like the UID can do in this milieu? Thin of the ecosystem for business it can create and spawn.....wow only.

What is striking about the small EKO team is that it includes graduates from India’s most prestigious institutes of technology who were working in America but decided to come home for the action, while the chief operating officer — Matteo Chiampo — is an Italian technologist who left a good job in Boston to work here “where the excitement is,” he said.

 Aha. Welcome home, Signor. Lest we forget America was made great also by a large swarm of skilled immigrants from all over the world - from German aerospace pioneers to desi silicon valley stars. India, traditionally has been this open land where ideas and immigrants from all over the world could come and mix and create and bedazzle. We lost that mojo somewhere in the past 1000 years but thanks to beginning made on 15 Aug 1947, we're well on our way to regain our traditional influence and place in the world, Heaven willing of course.

India today is this unusual combination of a country with millions of people making $2 and $3 a day, but with a growing economy, an increasing amount of cheap connectivity and a rising number of skilled technologists looking to make their fortune by inventing low-cost solutions to every problem you can imagine. In the next decade, I predict, we will see some really disruptive business models coming out of here — to a neighborhood near you. If you thought the rate of change was fast thanks to the garage innovators of Silicon Valley, wait until the garages of Delhi, Mumbai and Bangalore get fully up to speed. I sure hope we’re ready.

 OK. This is classic Friedman. Feel-good and all but better not to get carried away prematurely only. Actions speak louder than words and let the deeds of our entrepreneurs speak in making our country a better place for all its citizens to live in, while doing better than breaking even themselves.

Oh, might as well. On the same note is this splendid piece from Business standard by Arvind Singhal. Recommended read again and a better researched article than Friedman's.

The next five years (in the Indian Economy)

I believe it was some European CXO on a Des visit who remarked "A day in India is like a week in Europe." Yup, I guess.

India’s GDP in 2005 was about $785 billion, which has increased to almost $1,400 billion in 2010 and should cross $2,000 billion by 2015, implying that Indian economy would have added almost one India of 2005 to its size in the next five years. This spectacular growth, on a relatively high base of almost $1.4 trillion, translates into unprecedented opportunities and greater challenges than what India has faced in the past. Let us look at 2005 and then try to crystal ball 2015 for a few consumption categories.

Wow, eh? Jai ho, indeed.

In 2005, our domestic market for four-wheelers was just about 1.1 million vehicles. It will cross 2 million in 2010 and touch 4 million by 2015 (including as many as 110,000 in the luxury and premium segments). There were less than 100,000 users of smart-phones in 2005, about 25 million in 2010, and perhaps as many as 225 million in 2015. From a user base of about 8 million laptop users in 2010, there could be as many as 50 million by 2015. There were less than 25 million Internet users in 2005, increasing to about 75 million in 2010, and projected to grow to more than 250 million by 2015. From less than 250 multiplex screens in 2005, to about 800 in 2010, the count could cross 2,000 by 2015. Similar increases in multiples ranging from 2x-10x could happen across many consumer product categories.

..... Since the market opportunity is likely to grow in multiples of the current size, most businesses should rework their strategies and rewrite their business plans rather than just continue with incremental additions to their current plans.

But, as is often the case with Yindia, the challenges rise just as fast as the opportunities....only.

It is, however, more important to also give a hard look at the challenges that Indians and Indian businesses will encounter in the coming years. The first and more critical is the physical infrastructure. Doubling of number of cars and two-wheelers on the roads will need a corresponding increase not only in the road network but also in parking spaces, auto repair workshops and fuel vending stations. Adding of almost $400 billion in additional private consumption by 2015 will require a mind-boggling increment of nearly 1.5 billion square feet of retail space alone (or about 6,000 shopping malls of 250,000 square feet each). E-waste from the installed base of hundreds of millions of electrical and digital devices will run into tens of millions of tonnes, requiring enhancement of waste-management capacity by almost 10 times of what exists today. Steady increase in urbanisation will imply an additional demand for almost 20 million urban dwellings in cities where the infrastructure is already creaking to its limits. Strain on social infrastructure, be it education (primary, secondary, higher, and vocational) or health care (primary, secondary, and tertiary) or clean drinking water or sanitation will further increase manifold, rather just in simple double-digit percentages.

And so on and on. The next decade is crucial folk.s Make or break is it. We have to, and I mean have to, make the big push and enter the club of solid middle-income countries by 2020. There is no way in hell or highwater that we can afford to miss this bus, as we have done so often in the past.

Jai ho and Jai Bharat.

Websurvey latest news

Hi All,

As of now, some 2243 responses have flowed in. I thin its been great going so far.
Below is a pivot table with the # responses by group I have got at the time of writing. There's some glitch that is disallowing me currently from collecting more than 2000 responses, IT says it can be fixed.

Some concerns:
1. I'm told some ISB folk have filled up multiple surveys on behalf of multiple teams. This was precisely what I feared when allowing ISB folk to fill in surveys.

People, respondents' IP addresses are logged by qualtrics. Multiple surveys by within-ISB IPs will not be counted, pls be aware.

Also, within-ISB surveys are permitted only for foreign or exchange students only. Upto 10 responses from within ISB from each of such students is enough. Additional responses from within ISB for groups may not be counted for phase II, please be cautioned.


2. The fact that the final survey was hurried through and had to be released sans requisite pre-testing shows in that there are several ways in which the questionnaire could be improved. That said, however, we go with what we currently have. Let us make the best of what is out there currently.

Shall add more thoughts as they occur.

Sudhir

Websurvey Updates

Hi all,

The websurvey has already garnered some 1100+ responses.

Yay and Whew!

Great effort so far, teams. Let me hurry to add however that the above 1100 responses include quite a few by groups taking the surveys themselves to check the websurvey out.

Thanks to all those who wrote in with pointers to typos and other errors. We've accommodated what changes we could without changing the structure of the survey and invalidating past responses to particular questions.

How are groups doing? Well, here's a picture from a quick pivot I drew as of 1740 hrs Tuesday. Let me see if this comes up well....

Alright. There you go.

Update: Have been asked for a word doc copy of the survey. The argument is that this way groups can study  the questionnaire logic and better plan the analysis to come. I agree. I'll do one better, let me share with you the exec summary sheet that has been generated also. Shall ask the AAs to putup on the blackboard.


Sudhir

Websurvey Live Link

Hi Class,

Please find below the websurvey live link. 

https://isb.qualtrics.com/SE/?SID=SV_6EV6qH9ft6cKbOI

Pls forward to as many genuine respondents in the target population as you can find. KIndly do not forget to mention two things:-

1. Your group name. The respondent has to enter the name of the group that has forwarded the survey to him/her.

2. The incentives for survey completion - both monetary and data/information related.

If you detect any obvious issues with anything in the survey - typos, logical errors etc, let us know. There is cope to correct typos etc even while the survey is open.

Pls remember, the survey closes midnight Thursday (11.59 pm on 4-Nov-10). All valid and complete responses from each group obtained till then are counted towards the group's credit for phase II.

Sudhir

Errata from Lecture 7

Hi Class,

Lecture 7 deals with Causal research (Experimentation) and the analysis of variance. The two are together because they are connected - the former collects data which the latter is very well suited to analyze for inference, recommendations and action.

The hands-on work regarding running ANOVA models on different software - primarily JMP, Excel and R - in class today led to two errors for which reason I write this erratum online.

1. JMP by default seems to read all data in as numeric only.  In ANOVA, our independent variables, the Xs, are nominal/ categorical. So, JMP's reading them wrong resulted in the results being misleading as well. Even the ANOVA results JMP displays are nothing but the joint significance F-test which is computed on a linear model considering the Xs as metric.

The way out is to double-click on each column header and redefine the variable type to categorical/nominal. Then the thing runs fine and the results seem plausible.

2. Excel is not well-suited to doing ANOVA related work primarily because the data input it requires seems to need lots of prior editing.The data must be sorted and placed in arrays before Excel will read and analyze them. JMP is much better placed in this regard. R has its own issues. It does not give the joint significance F-stat and p-value.

So, bottom line - we stick with JMP as the best of the lot - after inputting data in the appropriate manner.

OK, more generally, there are two kinds of statistical tests that we do to conclude things one way or the other - tests of association that typically involve interdependent data, and those of dependence that involve dependent data. The stats primer started with basic model building - waded into over-identified systems and from there into models of dependence. The chi-square tests we saw last class were tests of association and today, we see a powerful battery of tests for dependence.

This has applications on the ground - not just in the project but for business problems, situations and issues you are likely to face at work. Take a re-look at your ELPs to see if the methods picked up could have come in handy. The reason I'm hard-selling data work and quant methods and what we have been doing in the past 2 odd lectures is that I get the vibe I haven't convincingly conveyed their importance, practical utility and breadth of applicability in real-life problems to a significant section of the class. 

Well, class, the going gets tougher, of sorts, here on. We're entering a rather dry part of the course involving analysis and some data work. My experience tells me that data work imparts real skills that are sale-able in the marketplace - whether explicitly or implicitly. It lends realism, credibility and perspective to the problem formulation and research design skills we learned in the early part of the course. So even if the lecture appears rather dry, dull and all, hang on. It will all connect together, not least through the project, to tangible knowledge learned and skills earned in the course of the course.

My apologies to sections A and B for the JMP issues that came up. My thanks to the folks who spoke up and pointed out the errors.

Sudhir