Previous studies on predicting the box-office performance of a movie using machine learning techniques have shown practical levels of predictive accuracy. Their works are technically-and methodologically-oriented, investigating what algorithms are better at predicting the movie performance. However, the accuracy of prediction model can also be elevated by taking other perspectives. For example, it is possible to increase the model accuracy by introducing unexplored features that might be related to the prediction of the outcomes. In this paper, we examine multiple approaches to improve the performance of the prediction model. First, we add a new feature derived from the theory of transmedia storytelling. Such theory-driven feature selection not only increases the forecast accuracy, but also enhances the interpretability of a prediction model. Second, we use an ensemble approach, which has rarely been adopted in the research on predicting box-office performance. As a result, the proposed model, Cinema Ensemble Model (CEM), outperforms the prediction models from the past studies using machine learning algorithms. We suggest that CEM can be extensively used for industrial experts as a powerful tool for improving decision-making process.2

The overwhelming supply of online information on the Web makes finding better ways to separate important information from the noisy data ever more important. Recommender systems may help users deal with the information overloading issue, yet their performance appears to have stalled in currently available approaches. In this study, the authors propose and examine a novel user profiling approach that uses collaborative tagging information to enhance recommendation performance. They evaluate the proposed hybrid approach, illustrated in the context of movie recommendation. The authors also empirically evaluate various existing recommendation approaches (in comparison with the newly proposed approach) using sensitivity analyses to investigate the potential use of varied user rating or tagging patterns to improve recommendations accuracy. The results don't just indicate the effective and competitive performance of the suggested approach, but they also suggest important implications and directions for further research, including the potential associated with applying multiple recommendation approaches within a single system based on the different rating or tagging patterns of the user.

No abstract

Consumers have been banking and trading online for several years now. More ambitious and tech savvy consumers have also been constructing an overview of their financial life by using Personal Finance software like Quicken and online tools such as Yodlee and Mint.com. Since late 1999, Personal Financial Aggregators (PFAs) have started offering internet based services to automate this process of account aggregation. This web account aggregation allows individuals to log onto one Web site and view all of their online accounts in one place. Online accounts that can be aggregated include financial sites (bank, credit card, brokerage, insurance, etc.) as well as lifestyle-based sites (travel awards, email, chat rooms, etc.). The idea behind Personal Financial Aggregation is to offer consumers their own personal portal from which they can see all their finances at a glance, balance and rebalance accounts, make investments, pay bills, etc. In addition to this Web data aggregation, consumers are relying on social media sites such as facebook, tweeter and other internet forums to get financial advice from each other and also to critique various financial products and services. As a result, many Financial Institutions (FIs) are using social media analysis and mining to shape their businesses. FIs include consumer banks, brokerages, insurance, wealth management firms, etc. This paper presents a framework for financial institutions that combines social media mining, web mining, online advice engines, and web aggregation. This framework can be utilized by FIs to analyze online buzz about their products/services and combine those insights with web aggregation and online advice to create different revenue streams and to offer personalized bundled products and services. The authors conducted interviews with various executives at the Global Financial institutions and insurance companies to test and validate this framework. A comprehensive review of top service providers and vendors that can enable and drive this framework is also discussed in this paper, followed by managerial implications, benefits and challenges.

No abstract