Week 5 – Vignette: Data Mining Goes to Hollywood
1. Why should Hollywood decision makers use data mining?
Data mining is a prime candidate for better management of this data-rich, knowledge-poor business environment.
2. What are the top challenges for Hollywood managers? Can you think of other industry segments that face similar problems?
A significant challenge for Hollywood managers is trying to predict box-office receipts of a particular motion picture. The movie industry is the “land of hunches and wild guesses” due to the difficulty associated with forecasting product demand. Any industry segment that needs to bring a new service or product to market suffers the same challenges of predicting how the customer base will react to the new product. Food products, electronics, artwork, clothing, and almost every industry you can think of that brings new products to market face similar problems.
3. Do you think the researchers used all of the relevant data to build predictive models?
I think the researchers identified meaningful data sources and intuitive data elements to build predictive models. However, I do not think they were able to use all available relevant data because the number of potential sources may be unknown to the researches as is all the potential element correlations which identify the less intuitive data elements. If the predictive model produces the desired accuracy, then they used enough relevant data to build the model.
Why do you think the researchers chose to convert a regression problem into a classification problem?
The idea of mapping regression into classification was originally used by Weiss & Indurkhya with their rule-based regression system. They used the P-class algorithm1 for class discretization as a part of their learning system. This work clearly showed that it is possible to obtain excellent predictive results by transforming regression problems into classification ones and then use a...
Please join StudyMode to read the full document