Working with Imperfect Data

Welcome to our Friday WRAP – one thought-provoking idea to think about over the weekend.

This week’s idea is about mitigating the uncertainty that come from analyzing a data set.  The thought comes from a recent Sloan Management Review article, Analytical Value from Data That Cries Wolf, written by Professor Sam Ransbotham from the Carroll School of Management at Boston College.

Professor Ransbotham suggests several steps to reduce uncertainty, among them is to use a portfolio approach.

If all the data in your analysis is from data sources that traditionally focus on reducing false positives, a data source that allows for false negatives adds insight. Choosing one or the other is a false dichotomy. In the hotel reservation example, the estimates of demand that combine prepaid reservations, no-commitment booking, and online availability search will outperform estimates based on only one source because each of the three data sources offers unique perspectives that, when combined, yield better insight to the true demand. Restaurants are embracing this approach by combining manual reservations from loyal customers, data from Open Table, and managerial insight.

In many contexts, predictive analytics is embracing data sources with a variety of perspectives. Uber blends multiple uncertain inputs to predict rider destinations and improve service. Looking at desserts on the menu doesn’t always lead to an ice cream order, but analytics at McDonalds incorporates the probability that it will. Airplane arrivals may not always translate to rental car demand, but Enterprise uses this signal to adjust staff and minimize wait. Even data rich in false positives can inform.

What data sources would compliment those you already use in your BI/Analytics activities? 

That’s a WRAP!  Have a nice weekend!