Wednesday, June 27, 2012

CRM Bloopers...

This post is on a lighter note. The software industry and the manufacturing industry are proud of their Quality Assurance processes. But it looks like CRM processes lag behind on this front.


Today I renewed my vehicle insurance policy. This is my first renewal and I have had a year of no claim on the policy. So I enjoyed a "no claim bonus" on the renewal premium. After completing the payment of the renewal premium, I was presented with the usual "thank you" message from the insurer, Bajaj Allianz. While reading the message I was very amused by the following sentence:

"As a loyal customer you are covered Additionally for Accidental Medical Expenses Cover/Drive Assure protect and 24x7 spot assistance for sum insured of Rs. 0."


So for renewing the policy, I am termed as a "loyal" customer. Well, I am okay with that. I get additional services. Well, I am okay with that. For a sum insured of Rs.0. WHAT? Is that a benefit I should be happy about? I can make two guesses:

1. Either it is a typo error. In which case, I will wait for the detailed policy wordings document.

OR

2. The formula used for calculating the benefit resulted in a value of ZERO.

Typical, case of borderline defect as they say in the software industry. A case for Quality Assurance.


On similar lines, a couple of months back, I was withdrawing some money at the ATM. After the transaction, I was presented with the following screen.



Note the options given. It was like holding a gun to my head and stating that I have to take the offer. There was no exit option or refusal option. The first time it happened, I was perplexed on what to do especially since my debit card was still in the ATM machine. I did not want the bank to call me since my CA had already addressed all tax issues. While my mind was booting up to process this situation, the screen went away and the transaction terminated normally with my transaction slip and card being returned to me. The next time, I got this message, I knew I had to just wait for few seconds and eventually the message would go away. DEJA VU... I say.



If you enjoy my posts, click on the right to follow these posts. Also, looking forward to your comments and similar experiences.

Monday, June 18, 2012

Integrating online and offline worlds


A few years ago I had written a post of my experience with a general insurance company. (Same Company ...Same Customer). This post highlighted how the company was giving different customer experiences across different channels. 

I have noticed a recent trend among my colleagues and myself included. Even when one purchases a product at the store outlet, one often visits online retailers to check options, comparisons and prices. In most cases, this online research also includes the web site of the outlet from where the product is eventually purchased. 

I have been working out on how the two worlds can be integrated for a retailer. The toughest format to integrate is the super market. These are stores with a high RFM value. I had a passing mention of this in my post on customer captivity (Aim for captivity .. not loyalty).  The relevant excerpt from this post is pasted below:

"Grocery purchases are often a chore rather than fun activity. A grocery retailer could allow a customer to define her basket of regular purchase. Then have an SMS facility wherein the customer sends in her request for a particular basket and have it delivered to her home. What a convenience that would be? Would this customer want to go over the pain of defining her baskets with another retailer... highly unlikely."

While the thought started with an idea, overtime I have fleshed out the model of integration between online and offline formats. The key aspect of this integration is unified customer experience across the channels. There should be a scenario wherein the customer feels that certain activity can only be done on the online or the offline format. I will attempt to highlight key aspects of the same in the post. 


  • The customer gets registered over the net or at the store. The mobile number is used as the identifier of the customer.
  • The customer can create shopping list over the net and store it. She can also give it unique and meaningful names..such as weekend, monthly, household, etc. 
  • The customer can also create a shopping list by SMSing the receipt number to a predefined number. The backend system would retrieve the purchase basket of the receipt number and store the basked as a shopping list against the customer account. The customer can copy or modify the list as per requirement. Also, the feature to specify brands or leave it open for each item is available to the customer. 
  • When the customer needs to shop for specific items, say household items on a monthly basis, the customer will need to send an SMS to the predefined number with the shopping list name or number. The customer can also order for the shopping basket over the net. Based on the delivery preferences, the basket is then delivered to the customer. 
  • Over time, the purchase pattern can be identified for each customer. Using analytics, one can predict the likely basket and the time of purchase. As this time nears, the retailer can prompt the customer for upcoming need. This could also be a reminder call for the customer who probably just needs to confirm the basket and have it delivered to her. 
  • In order to increase the basket, the retailer can used market basket analysis to recommended additional products to be added to the basket. Also, personalized offers could be presented to  the customer. 
  • The customer can also order a shopping list over the web and opt to have it ready for pickup at a particular outlet. While at the outlet, maybe she wanted additional items which she wants to inspect before purchase. This also gives opportunity for impulse purchase while she is at the store. The customer saves time picking up items of regular purchase in her basket. 
  • On lines of fast food joints, the above basket could also be in a drive-in lane where the customer can pick it up at the take-away counter and pay for it without leaving her vehicle.
  • The retailer could also offer products on trial to entice purchase. This is corollary to the product association analysis that determines the next best product. In this case we look at products that are least likely to be bought by the customer but one that if enticed the product has best chance to be bought. For example, the profile of the customer shows that she has a school going youngster in her household. Our basket analysis shows the "school" related products that the customer has bought. The disassociation analysis also shows the products that the customer has not bought and is least likely to buy. A conditional modelling can show the product amongst this second set that has the best chance of being bought if the customer is enticed with the product. Such a product can be given to the customer on a trial basis to be returned within, say, 15 days if the customer does not want it. The customer can opt to purchase it and be billed in the next purchase basket.  
  • Additional service, such as toileteries and personal effects can be made available in different cities to be delivered to the customer when she is travelling. 


If any retailer wants to run a pilot on this, kindly contact me at michaeldsilva@gmail.com. Together we can define an appropriate process for blurring that online / offline demarcation and provide a unified and enhanced customer experience.

Monday, June 11, 2012

Segmentation .... now or later?


Very frequently while building analytical models, I have had clients state "Let's start with customer segmentation." I have to spend a considerable time convincing the clients that segmentation is not mandatory as the first step of modelling. Unfortunately, a majority of the statisticians start with segmentation. They claim that the population need to be clustered into homogeneous segment. Every business user also is convinced that his customer base is a group of homogeneous clusters.

This thinking is very flawed for two reasons:

  1. Segmentation is a relative activity. That is, one needs to do "statistical" segmentation towards some goal... whether it is to understand customer value or default or cross sell. Segmentation as a stand alone activity does not provide much value. This is the reason I always dissuade my customers from doing just a "segmentation" exercise. (see my post on "statistical segmentation" titled perspectives of segmentation).
  2. Grouping customers into clusters induces biasness into the model building process. Let me elaborate further on this.


The primary reason in clustering is that the customer base consists of groups of individuals who behave in similar pattern. This also leads to the corollary that customers belonging to different clusters behave differently.

My econometrics professor in college had a wonderful way of explaining statistical concepts from real life scenarios or philosophies. He had stated that the basic premise of law is "a person is innocent unless proven guilty." He had told us to keep this premise in mind when defining the hyphothesis for model building. Going by this, we start with the assumption that the customer population is homogeneous unless proven otherwise. This proof can only come with model building.

By performing segmentation upfront, we are making an assumption that the customer population is not homogeneous. With this presumption we are inducing a biasness in the model building process.

From an effort perspective, I have a cost accountant view on this. A segmentation exercise typically leads to definition of 5 to 10 segments. The next step will be to build separate models for each of the 5 (or 10) segments. This multiplies the efforts required. And all because of an unproven assumption that different segments behave differently from one another.

An effective approach will be to first assume that the customer base is homogeneous. Then build a single model for the target variable. The next step is to find variance within the test population. The variance can be either on the decile dimension or we could look at the significant variable to idenfity the value that has the highest variance. This will then indicate a likely set of customers who behave differently than the rest of the population and hence provide the variance in the test population.

At one client where we adotped this approach, we found that the "product holding" was showing the highest variance. Evaluating the values, a particular product was found to be exhibiting the high variance. As a next step, we split the population into two segments -- one segment holding this product and the second for the rest of the population. Two separate models were built, one each for the two segments, and the scores were merged (after normalization). Since the population creating variance in the original model was now separated, the rest of the population was comparatively more homogeneous. The model for the variant population was custom for that population and hence a better fit. Thus, the combined scoring was more accurate than the first single model. This accuracy met the acceptable threshold of the client and we deployed the score in the business operations.

The entire exercise involved - 3 models and one filter based population split. Compare this with the "traditional" approach of one segmentation (leading to 5 to 10 segments) and one model for each segment (approximately 5 to 10 segments). We completed the exercise in 4 days against what would have taken us more than 10 days the traditional way.  
 
test