Movie forecast Guru: A Web-based DSS for Hollywood managers

Delen, Dursun; Sharda, Ramesh; Kumar, Prajeeb

doi:10.1016/j.dss.2005.07.005

Cited by 78 publications

(50 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Similarly to the modeling phase, the best results are given by the NN model and for both metrics, with improvements of: 2.7 pp for SVM, 3.7 pp for DT and 7.9 pp for LR, in terms of AUC; and 1.6 pp for SVM, 2.1 pp for DT and 4.6 pp for LR, in terms of ALIFT. Interestingly, while DT was the worse performing technique in the modeling phase, prediction tests revealed it as the third best model, outperforming LR and justifying the need for technique comparison in every stage of the decision making process [9]. Table 5 Comparison of models for the rolling windows phase (bold denotes best value) When comparing the best proposed model NN in terms of modeling versus rolling windows phases, there is a decrease in performance, with a reduction in AUC from 0.929 to 0.794 and ALIFT from 0.878 to 0.672.…”

Section: Predictive Knowledge and Potential Impactmentioning

confidence: 99%

“…For instance, SVM provided better results in [6] [8], comparable NN and SVM performances were obtained in [5], while DT outperformed NN and SVM in [24]. These differences in performance emphasize the impact of the problem context and provide a strong reason to test several techniques when addressing a problem before choosing one of them [9]. DSS and BI have been applied to banking in numerous domains, such as credit pricing [25].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A data-driven approach to predict the success of bank telemarketing

Moro

Cortez

Rita

2014

Decision Support Systems

680

373

View full text Add to dashboard Cite

We propose a data mining (DM) approach to predict the success of telemarketing calls for selling bank long-term deposits. A Portuguese retail bank was addressed, with data collected from 2008 to 2013, thus including the effects of the recent financial crisis. We analyzed a large set of 150 features related with bank client, product and social-economic attributes. A semi-automatic feature selection was explored in the modeling phase, performed with the data prior to July 2012 and that allowed to select a reduced set of 22 features. We also compared four DM models: logistic regression, decision trees (DT), neural network (NN) and support vector machine.Using two metrics, area of the receiver operating characteristic curve (AUC) and area of the LIFT cumulative curve (ALIFT), the four models were tested on an evaluation phase, using the most recent data (after July 2012) and a rolling windows scheme. The NN presented the best results (AUC=0.8 and ALIFT=0.7), allowing to reach 79% of the subscribers by selecting the half better classified clients. Also, two knowledge extraction methods, a sensitivity analysis and a DT, were applied to the NN model and revealed several key attributes (e.g., Euribor rate, direction of the call and bank agent experience). Such knowledge extraction confirmed the obtained model as credible and valuable for telemarketing campaign managers.

show abstract

Section: Predictive Knowledge and Potential Impactmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

A data-driven approach to predict the success of bank telemarketing

Moro

Cortez

Rita

2014

Decision Support Systems

680

373

View full text Add to dashboard Cite

show abstract

“…Delen etc. constructed an estimation model of film box office based on the type of film, star, technical effect, release time and other characteristic parameters to establish a Web decision support system [19]; Ghiassi et al, set up a dynamic artificial neural network prediction model according to the advertising budget, release time and seasonal forecast variables [20]; Zheng Jian put forward a kind of the movie box office forecasting model based on feedback neural network [21], whose output can not only be more reliable to reflect the movie box office income during the on-showing period, but also point out the range of that; Jing Fei et al, used machine learning methods to make statistical analysis by the information of Microblog, proposing a box office estimating method based on Microblog [22]. By these kinds of prediction and analysis methods based on big data, it is uncomplicated for cinema circuits to make more accurate choice of films.…”

Section: Big Data In Film Broadcastingmentioning

confidence: 99%

The Big Data Applications in Film Industry Chain

Wang¹,

Wang²,

Chai³

et al. 2016

IJDTA

View full text Add to dashboard Cite

“…An obvious line of argument points out that a project features elements identified as beneficial in success factor studies. The numerous proposed forecast models (Sawhney & Eliashberg, 1996;Neelamegham & Chintagunta, 1999;Eliashberg et al, 2000;Chang et al, 2005;Hennig-Thurau et al, 2006;Delen et al, 2007) can be used to determine an expected value of audience interest and thus quantify consumption risk. Thus, it can be assumed that crucial success factors such as content attributes, personnel traits and funding also indicate the relevant areas of risk management in the development phase.…”

Section: Controlling Risks In Movie Projectsmentioning

confidence: 99%

Managing Risk in Motion Picture Project Development

Rimscha

2009

Journal of Media Business Studies

View full text Add to dashboard Cite

Movies are produced as unique prototypic media content to serve a highly uncertain demand. Film producers have to address the consumption risk while their projects are still in their development phase. This paper provides a literature review of key risk dimensions of movie projects and how to control them. The interviews conducted with movie producers have made it possible to compare the industry's risk control strategies. Content attributes, personnel, and funding emerge as key project resources and risk reducing elements both in theory and practice. Three distinct risk control strategies are identified and assigned to different resource configurations and market constraints of individual producers. Managing Risk in Motion Picture Project Development M. Bjørn von RimschaUniversity of Zurich ABSTRACT Movies are produced as unique prototypic media content to serve a highly uncertain demand. Film producers have to address the consumption risk while their projects are still in their development phase. This paper provides a literature review of key risk dimensions of movie projects and how to control them. The interviews conducted with movie producers have made it possible to compare the industry's risk control strategies. Content attributes, personnel, and funding emerge as key project resources and risk reducing elements both in theory and practice. Three distinct risk control strategies are identified and assigned to different resource configurations and market constraints of individual producers.KEY WORDS: project management, project selection, movie producer, industry structure, project resources This paper focuses on the development phase of movie production in which projects are selected rather than on movie distribution; it concentrates on producers developing a movie package rather than production companies building a portfolio of several movie projects.

show abstract

Movie forecast Guru: A Web-based DSS for Hollywood managers

Cited by 78 publications

References 28 publications

A data-driven approach to predict the success of bank telemarketing

A data-driven approach to predict the success of bank telemarketing

The Big Data Applications in Film Industry Chain

Managing Risk in Motion Picture Project Development

Contact Info

Product

Resources

About