No abstract

Artificial intelligence has been increasingly employed to improve operations for various firms and industries. In this study, we construct a box office revenue prediction system for a film at its early stage of production, which can help management overcome resource allocation challenges considering the significant investment and risk for the whole film production. In this research, we focus on China's film market, the second-largest box office in the world. Our model is based on data regarding the nature of a film itself without word-of-mouth data from social platforms. Combining extreme gradient boosting, random forest, light gradient boosting machine, k-nearest neighbor algorithm, and stacking model fusion theory, we establish a stacking model for film box office prediction. Our empirical results show that the model exhibits good prediction accuracy, with its 1-Away accuracy being 86.46%. Moreover, our results show that star influence has the strongest predictive power in this model.

We introduce reference dependence to describe the fairness utility functions of channel members and model a dual-channel supply chain (one manufacturer and one retailer) in three scenarios: only the manufacturer is concerned with fairness, only the retailer is concerned with fairness, and both parties are concerned with fairness. The ordering decisions and coordination of a dual-channel supply chain under the online-to-offline (O2O) business model are studied. Nash equilibrium solutions exist for the channel order quantities in all three scenarios, and the inventory transshipment strategy can be used to coordinate the dual-channel supply chain under the O2O business model. Numerical examples are used to analyze the effectiveness and feasibility of coordination. The inventory transshipment strategy can be used to directly coordinate the dual-channel supply chain when only the manufacturer is concerned with fairness. The retailer feels unfair in the other two scenarios, which affects cooperation. To maintain cooperation with the retailer and achieve optimal supply chain efficiency and channel coordination, the manufacturer must compensate the retailer or choose one with fewer expectations regarding its channel status or fewer fairness concerns.

The vulnerability assessment indicator system (VAIS), including the tourism economic sensitivity and respondence, is modified and established in this paper. According to the collected data, during 2014–2018 of the 31 provinces of China, of the tourism economy sensitivity and respondence, the improved comprehensive evaluation projection pursuit clustering (PPC) model is established, and the vulnerability indexes of the 31 provinces are calculated, thus expanding the tourism economic vulnerability assessment methods. Our empirical results show that, during the period of 2014 to 2018, the sensitivity, the respondence, and the vulnerability indexes are unbalanced overall. The tourism economy sensitivity and the respondence show that the spatiotemporal distribution characteristics are high in the east and low in the west. On the contrary, as for the vulnerability, the spatiotemporal distribution characteristics are low in the east and high in the west. Among the 40 indicators, the ratio of industrial solid waste utilized (%), urbanization rate, and the density of grade highway and railway network (km/km2) have the greatest impact on the respondence, while the proportion of the population affected by natural disasters, the diversification index of industrial structure, and the number of traffic accident casualties have the most significant impact on the sensitivity, which are the indicators that have the greatest impact on vulnerability. Therefore, in order to effectively reduce sensitivity, improve respondence, and thus reduce the vulnerability index of the tourism economy, the provinces should first improve the above-mentioned evaluation indicators with the largest weights. Our research results in this paper enrich the theory of sustainable development of the tourism industry and derive managerial and policy insights for further achieving the high-quality development of the tourism economy.