Tag Archive for 'Predictive Analytics'

Keeping Predictive Models Current: Dealing with Continuous Change…Continuously

Published on March 4, 2010 in Nat Evans. 0 Comments Tags: , , , , , , , .

by Nat Evans, Pitney Bowes Business Insight

Most contemporary predictive models, which forecast performance such as sales, customer visits, membership levels, etc., are based on historical data that create “snapshots in time,” using whatever relevant sources were current at the time of analysis. Examples include POS distributions, store and competitive locations, store sales performance and demographic data. But we know operations and the environment changes as soon as a model is completed and put into use. As a result, model accuracy erodes with each passing day as the data inputs into the model or the benchmarks upon which expected performance are based become stale. To be sure, most site selection professionals and researchers attempt to make sure models are as fresh as possible, updating these data elements on a regular and recurring basis. During recent engagements with several long time clients, we have been asked if there was a way to take into consideration dynamic time series data elements to help with forecasting and minimizing risks.

What do we mean by dynamic data?

Many factors may play pivotal roles in retail forecasting and market prioritization. Depending on the level of aggregation, the obvious thought is that a researcher may be able to affect a change in market conditions or individual sales estimates, depending on the application. Indeed, they can significantly sway analyses enough to change even the simplest of decisions, either minimizing risks (if used appropriately) or increasing a company’s vulnerabilities, especially given the current macro-economic climate.
A couple of sources of dynamic data within the context of a static model may include:

• Macro-economic data such as housing starts, CPI (consumer price indices), funds rates, and unemployment percentages either nationally or at varying levels of macro geography – state, county, or CBSA. Such measures provide a look into the health of consumers’ collective behavior, and depending on how the analysis is structured, whether these factors will be leading or lagging indicators of retail growth and consumer spending (PBBI has created an approach-MarketPulse-that incorporates these factors into predictive models).

• Gas prices. Gas price fluctuations on a regional or even local level can create a similar effect that macro-economic variables may produce in models. Obviously, the higher gas prices rise, the less disposable income consumers will have to purchase goods and services, potentially depressing actual local store performance. Distance may become a stronger deterrent to patronage as a result.

If a retailer’s or restaurant’s sales forecast model was created in better times, it may produce a “false positive,” inappropriately triggering a go/no-go decision and costing company valuable resources and capital from other locations that may be more profitable. Just as importantly, if a company is judging a general or district manager on existing location(s) sales performance based on a projection created earlier in the fiscal year, the company may be unduly influencing that leader’s performance rating on factors outside of his or her control.

How can we create more flexible models using dynamic data?

There exists a myriad of ways we can leverage dynamic data through any forecasting or analytical process, more generally. The important point with any data source is to leverage any and all relationships that may prove fruitful through the forecasting process. But, it must be relevant to your research design, have purpose, and be significant enough to warrant using in modeling and analytical review.

In the future, the ability to collect and cleanse data continuously not only from existing, well-documented sources, but also new sources, such as e-commerce and online social/behavioral data, will become more available and increasingly important across any organization. Additionally, whether on-premise or in the “Cloud”, the technology that facilitates a seamless data flow into predictive applications should enable decision-making with the most up-to-date analysis possible.

Consumer Demographic Profiling: Does Distance-weighting Make a Difference?

Published on November 20, 2009 in Nat Evans. 0 Comments Tags: , , , .

Nat Evans, Pitney Bowes Business Insight

It is a standard market research practice to use psychographic segmentation as a primary tool for discerning a company’s target customer.  This “customer profile” creation is a primary means by which customer behavior is bucketed into distinct groups that reflect differing customer characteristics, shopping behavior and loyalty to a retail, restaurant, or consumer package brand.

Over time, the Strategy & Analytics statistical modeling team at PBBI has given a lot of thought to the idea that customer profiles, and their use in sales forecast models, may be enhanced by weighting the customer source survey data by distance.  It makes sense.  The farther away target (or non-) customers are, the more pronounced the profile scores may be.

For instance, a typical customer profile for a high-end department store, with a specific high income, suburban customer segment or “cluster” (Corporate Clout, say, from Acxiom’s PersonicX lifestage segmentation system) may have a score of 200, meaning that people within the segment spend two times what an average customer spends for the concept.  A low-income segment (Single City Stress, for example) may have an index score of 40, or the segment spends 40 cents for every dollar that an average customer spends. Weighting the profiles by distance, however, may yield a more intensified result.  You may expect the high-income cluster to go from an index score of 200 for customers only within 0 to 3 miles, to 225 for those same customers beyond 6 miles from any given store.  Perhaps the Single City Stress cluster would go from 40 to 25, meaning that the farther away the cluster is from the store, the less they are willing to patronize and spend at the department store relative to other customer segments at the same distance.

In theory, it seems to be a reasonably insightful approach.  In practice, the S&A modeling team created just such an analysis, and found that among several clients’ customer databases, distance has no significant bearing on the relative spend of psychographic segments at the same distance.  The following box plot will give a sense for one sample profile’s distribution:

Distance Weighted
As shown, 50% of all scores’ distributions fall between approximately 50 and 110.  A couple of outlying clusters find themselves floating outside the distributions (the “1”, “2”, or “3” above the whisker for each plot), but statistically, no significant difference was found between scores at different distance increments.  The distributions’ medians were roughly the same; variance was the same.  This pattern was consistent among several customer files we tested, and the application of several distance weighting methods yielded no statistically significant enhancement whatsoever.  Goes against the hypothesis.  To be sure, there exists a multitude of ways to carve up customer data, and this analysis is by no means definitive, but from a macro level, it seems the proof is in the data. This analysis also does not mean that distance in its myriad forms (straight-line, drive time, drive distance) has no influence.  Obviously, it does.  Distance decay portrayed on a sales per capita, or other relevant, basis is very important indeed, and is an extremely well documented predictor of consumer behavior.  It’s just a matter of proper application, and what any one retailer’s customer data is truly telling an analytics researcher.

PBBI Retail Practice Leader Appears in Retail Traffic Magazine

Published on November 16, 2009 in Leslie Nogue. 0 Comments Tags: , , , , .

In the October issue of Retail Traffic, Associate Editor Elaine Misonzhnik interviewed Devon Wolfe, Managing Director of Americas Strategy and Analytics Services with Pitney Bowes Business Insight, for her story on current site selection trends.

In the article Forced to Count Every Dollar, Retailers Re-evaluate Site Selection Practices, Devon assesses the current state of retail site selection, which is showing signs of growth, despite the economic downturn. In today’s economy, retailers are holding themselves to much more stringent criteria when assessing the viability of a new location. The industry push for accurate, up-to-the-minute information on a market by market level highlights the importance of macroeconomic data when retailers are evaluating market potential for new stores. Today, retailers need visibility into “statistics on employment figures, GDP growth, retail sales and the number of bankruptcy filings”. It is for this reason that Pitney Bowes Business Insight introduced MarketPulse, a quarterly subscription to a detailed macroeconomic report that provides insight into market level trends. [Read entire article...]

Retail Traffic is a monthly magazine written for senior level retail executives.

Attack Back With Financial Literacy

Published on November 11, 2009 in Brian Diepold. 0 Comments Tags: , , , , , , .

Brian Diepold, Pitney Bowes Business Insight

You couldn’t go ten minutes at BAI Retail Delivery without hearing about – or talking about – NSF fees. It’s natural that it would be a hot topic as it is certainly getting its share of media and congressional attention these days. Richard Davis made a great point that the industry needs to educate Congress and the public that these fees are not necessarily immoral – after all, as he so nicely pointed out, we are providing a service for the consumer and we are charging for that service.  I agree, and we need to take Mr. Davis’ advice that we need to tell the story in a more positive light.

I also think it’s important that we do more to educate our consumers. This economic crisis is very tightly linked to the lack of economic education and financial literacy in our country. We don’t do enough as a society to arm our population with the necessary tools to think about the world the same way we do as bankers, financial advisers, and economists. Not everyone needs to have a passion for these topics, but they certainly need to have a basic understanding in order to manage their personal finances. The national and state councils on economic education do everything they can to support these initiatives for our youth, but we also have an adult population that lacks this knowledge.

Let’s take it upon ourselves to help solve that problem. Banks could generate goodwill by offering simple educational programs at the point of sale. Let’s take 15 minutes to teach a new customer how to use their checking account. This may just allow them to avoid the extra fees down the road, while at the same time allowing you to guide them to being a profitable customer in other ways.

Not only is it good for the customer, but it would have to go a long way to convincing Washington that we are serious about addressing the issue ourselves – without Congress imposing their own solution.

Worst case – you are the only bank in your market that makes this effort. In that case, it should allow you to differentiate your offering and build that goodwill or brand value with the market. It’s a win-win.

Are American Retailers Ready for a Universal Reward Program?

Published on November 9, 2009 in Eric Steckling. 0 Comments Tags: , , , , .

Eric J. Steckling, Pitney Bowes Business Insight

As Democrats work toward a universal healthcare system for America, should American retailers take a cue from Canada and support a universal rewards program?

The Air Miles reward program in Canada has been in business for about 17 years and is supported by over 100 retailers (including retailers in the U.K., Spain, the Netherlands and several Middle Eastern countries). The Air Miles program has a fanatical following among its 9.5 million collectors. Parent company LoyaltyOne touts that 97% of Canadians know about the Air Miles program. So if the program is so successful in Canada why hasn’t a similar program been deployed state side? Well, they tried. The Air Miles program was introduced in the U.S. at the same time as the Canadian version in 1992, and was picked up by several national retailers. The U.S. program was shortly there after deemed unprofitable and discontinued in May 1993.

American retailers understand the value of customer loyalty programs, and many companies have developed their own programs. We are all familiar with Delta Skymiles, the Kroger card, CVS ExtraCare and our credit card’s Reward Points systems. Just take a look on your key chain or in your wallet. How many loyalty cards do you carry around every day? Retailers and consumers could benefit from a more universal system. The idea is simple: customers sign up for one program and are able to trash their wallet full of cards. Retailers join on the program and dole out the “points” at their discretion, and then benefit from a larger base of customers carrying a universal card. This will allow participating retailers collect more data about their customer’s shopping patterns than with a proprietary system. It will also allow smaller regional retailers to join into a loyalty program rather than create their own from scratch. As simple as the idea sounds, implementation of such a system would face many challenges and push back from multiple constituents, including retailers worried about margins or derailing their existing reward program and consumers wary of giving out personal information or losing benefits they have already earned.

The whole truth is that for retailers, the customer data that is collected from a reward program may be more valuable than the loyalty they generate. Participation in a universal program would mean more data for all. Those of us in the predictive analytics field are well aware of the value and usefulness of recording point-of-sale data and being able to link it with a specific customer. The retailers who collect and use this data gain efficiency in efforts including marketing, store planning, and product promotion to name a few. The barriers for a universal system are high, and pose a chicken and the egg dilemma between consumers and retailers: Without the critical mass of supporting retailers, consumers have no need to participate in the program. If the consumers are not signed up and participating, then where is the benefit for the retailers? And would Americans willingly supply one “big brother” company with all their spending data?

This initial failure of the Air Miles program in the U.S. may have been in part due to a translation issue. What do airline miles have to do with gas or groceries? Or an American need for instant gratification, why collect points when I could save money NOW?! One would think that if the program is so popular north of the border with our metric neighbors, shouldn’t it be called Air Kilometers?

The Value of Fielded Evaluations in the Site Selection Process

Published on October 27, 2009 in Ed Borden. 0 Comments Tags: , , , , , .

Ed Borden, Pitney Bowes Business Insight

Do you ever miss a football game, but read the stats after the game and say “wow, that was a pretty close game – final score 23 -21”. However, if you had actually seen the game in person you would have realized that one team dominated the game for three quarters, but only by a series of miss steps, did the second team have the ability to win the game at the last minute. We see this happen every weekend in the fall – the stats and numbers alone do not provide you with the full flavor and scope of the game… who was better or was the victory deserved. This is similar to the site selection process.

Far too often, businesses are so focus on the numbers, demographics/psychographics characteristics, traffic counts, distance to the nearest competitor, etc. that they do not value the intangible, qualitative aspects of a potential site that can only be garnered from an impartial fielded site evaluation. Even if you are visiting a proposed deployment site for a day, you can gain true insight for answering the questions:

  • How good is the ease of access and traffic patterns around the proposed site?
  • Do the surrounding neighborhoods appear to be trending up or trending down (are the homes well maintained or are there foreclosures)?
  • Are there demographic barriers to the site? – “don’t be caught on the wrong side of the tracks”
  • Do the surrounding shopping centers appear to be stable or are they losing retailers (especially national nameplates)?

Because of this intangible, difficult to generate in-house data, we believe that an impartial fielded evaluation of the site should always be conducted. This fielded evaluation can be done by either an outside organization or by an in-house research team. Too often field evaluations are left strictly to the real estate teams, who may not be completely impartial, as they typically have a vested (and compensated) interest in the new deployment (whether successful or not). Our organization has done fielded evaluations for many, many clients and has effectively seen most of the US and Canada, consequentially we have market knowledge that others do not and we can better judge one site versus another more objectively.

Whether you are opening a retail outlet, restaurant, bank or health center, in these challenging economic times, when it is so crucial that new units open to plan, there is real value in paying the relatively low cost of airfare, lodging and time for an impartial professional, either internal or external, to see the site and provide the “flavor” of that site to the forecast, and not to just rely on the in-office generated numbers.