April 2, 2012 in Thinking Analytically
Rating movies
SHARE: PRINT ARTICLE:
https://doi.org/10.1287/LYTX.2012.02.15
Retailers invest heavily in predicting how customers will rate new productions such as movies, books, games and appliances. Accurate recommendations lead to increased revenue and happier customers. To make these recommendations, retailers look for correlations between different products in order to make suggestions on what other products a customer might like.
Table 1 shows movie ratings from five customers for five movies. The ratings range from 1 to 5. A rating of 5 indicates that the movie was very highly liked and a rating of 1 indicates that it was not liked at all. One movie rating is missing because Evan has not yet seen the movie “Prognosis Negative.”
Question:
Using only the data in Table 1, what is the most likely rating that Evan will give to the movie “Prognosis Negative”?
Send your answer to [email protected] by May 31. The winner, chosen randomly from the correct answers, will receive an “Analytics: Driving Better Business Decisions” T-shirt.
John Toczek is the AVP Predictive Modeling at Chubb in the Decision Analytics and Predictive Modeling department. He earned his BSc. in Chemical Engineering at Drexel University (1996) and his MSc. in Operations Research from Virginia Commonwealth University (2005).