Changan Zhang

Imputing unknown competitor marketing activity with a Hidden Markov Chain

This paper demonstrates via a case study on two competing products at a bank how practitioners can use a Hidden Markov Chain to estimate missing information on a competitor’s marketing activity. The idea is that, given time series with sales volumes for products A and B and marketing expenditures for product A, as well as suitable predictors of sales for products A and B, it is possible to infer at each point in time whether or not it is likely that marketing activities took place for product B. The method is successful in identifying the presence or absence of marketing activity for product B about 84 per cent of the time. The authors allude to the issue of whether, if one can infer marketing activity about product B from knowledge of marketing activity for product A and of sales volumes of both products, the reverse might be possible and one might be able to impute marketing activity for product A from similar knowledge of product B. This leads to a concept of symmetric imputation of competing marketing activity. The exposition in this paper aims to be accessible and relevant to practitioners.

Visualization of Very Large Networks: The Co-starring Social Network

This chapter describes and contrasts two main approaches to visualizing the very large actor co-starring network. Technical details on how to construct the visualizations are provided and memory problems discussed. The chapter demonstrates a successful use of k-core techniques for visualizing large networks.

Movie analytics: Visualization of the co-starring network

This poster contributes a novel application of social network visualization techniques to the motion picture industry. We make the case and illustrate with examples that a visualization approach based on k-cores helps alleviate otherwise inextricable memory issues in analyses of the IMDb co-starring network, which contains more than 2.6 million actors displaying over a billion links, with degrees which can rise to about 50,000 and above for the most connected actors.

Movie Analytics and the Future of Film Finance. Are Oscars and Box Office Revenue Predictable

This chapter discusses to which extent modern analytics techniques can help us understand the success of movies, as measured by their box office or attributed Oscars. Interesting lessons emerge from our analyses. Predicting box office revenue on the basis of data available before the release of the movie remains difficult, even with state-of-the-art techniques. Prediction markets are a remarkably powerful tool at predicting success at Oscars. A moderate amount of controversy, as measured by the number of underlying themes raised by movie reviewers, may prove to be helpful in obtaining an Academy Award for Best Picture .

What Do We Know About Analyzing Movie Data

This chapter gives a road map of the topics discussed in the monograph and briefly introduces what is meant by “Movie Analytics”.

Movie Attendance and Trends

This chapter demonstrates how to analyze longitudinal data on weekly attendance during several years in eight different movie theaters in France, all located in small to medium sized cities in the South West part of France (the movie theaters considered in this study have from 1 to 4 rooms). Necessary R code is included and discussed.

Can We Predict Oscars from Twitter and Movie Review Data

In this chapter, we focus the attention on whether text reviews of movies which are nominated for a Best Picture award carry any sign of the likelihood of a movie winning the award. We suggest that a measure of how controversial the movie is perceived to be, the value of which could be extracted by a text analysis of the reviews, is a potential predictor of a win, aside from other predictors identified in past work. This also is an opportunity to discuss text mining and sentiment analysis techniques.

Oscar Prediction and Prediction Markets

In this chapter we examine the role of prediction markets in evaluating the probability of a nominated motion picture receiving an Academy award. We illustrate the issue with the best picture award in 2013.

Optimization of the promotion mix in the healthcare industry

Purpose – The purpose of this paper is to propose data mining techniques to model the return on investment from various types of promotional spending to market a drug and then use the model to draw conclusions on how the pharmaceutical industry might go about allocating promotion expenditures in a more efficient manner, potentially reducing costs to the consumer. The main contributions of the paper are two-fold. First, it demonstrates how to undertake a promotion mix optimization process in the pharmaceutical context and carry it through from the beginning to the end. Second, the paper proposes using directed acyclic graphs (DAGs) to help unravel the direct and indirect effects of various promotional media on sales volume. Design/methodology/approach – A synthetic data set was constructed to prototype proposed data mining techniques and two analyses approaches were investigated. Findings – The two methods were found to yield insights into the problem of the promotion mix in the context of the healthcare i...