Predicting Self‐declared Movie Watching Behavior Using Facebook Data and Information‐Fusion Sensitivity Analysis

Abstract

The main purpose of this paper is to evaluate the feasibility of predicting whether yes or no a Facebook user has self‐reported to have watched a given movie genre. Therefore, we apply a data analytical framework that (1) builds and evaluates several predictive models explaining self‐declared movie watching behavior, and (2) provides insight into the importance of the predictors and their relationship with self‐reported movie watching behavior. For the first outcome, we benchmark several algorithms (logistic regression, random forest, adaptive boosting, rotation forest, and naive Bayes) and evaluate their performance using the area under the receiver operating characteristic curve. For the second outcome, we evaluate variable importance and build partial dependence plots using information‐fusion sensitivity analysis for different movie genres. To gather the data, we developed a custom native Facebook app. We resampled our dataset to make it representative of the general Facebook population with respect to age and gender. The results indicate that adaptive boosting outperforms all other algorithms. Time‐ and frequency‐based variables related to media (movies, videos, and music) consumption constitute the list of top variables. To the best of our knowledge, this study is the first to fit predictive models of self‐reported movie watching behavior and provide insights into the relationships that govern these models. Our models can be used as a decision tool for movie producers to target potential movie‐watchers and market their movies more efficiently.

Main consumer choice drivers for fi lm products in the Russian market

“…Для решения задачи прогнозирования кассовых сборов фильма в некоторых исследованиях используются различные алгоритмы машинного обучения, основанные на данных, доступных перед выходом фильма в прокат (Park, Lim, 2021). Более новые модели используют 35 параметров фильма из 3200 фильмов в качестве входных данных для прогнозирования прибыли, полученной от фильма, и классификации успеха фильма от «провала» до «блокбастера» на основе полученной прибыли (An et al, 2021;Bogaert et al, 2021). В исследованиях также представлен анализ тех или иных архитектур машинного обучения, способных предсказать прибыль, полученную в результате проката фильма, с точностью до 85,31% без использования какой-либо информации о продажах (Abidi et al, 2020;Mahmud et al, 2020).…”

Three cobblers worth the mastermind? The potential of ensemble in crowdsourced classification problems

“…One of the most famous contests—the Netflix Prize (Bell & Koren, 2007)—also allowed the Netflix company to adopt the ensemble method to attain a powerful recommendation engine. Similarly, other business applications, such as financial fraud detection and movie watching behavior modeling, benefited from following a framework of ensemble (Abbasi et al., 2012; Bogaert et al., 2019).…”