Forecasting Case Study

Forecasting Case Study: Find a forecasting in service case study and share its summary with the class. Reference your material properly…

Forecasting Case Study

Paper details

Find a forecasting in service case study and share its summary with the class. Reference your material properly.

 600 words min.

Forecasting in Services in Korean Film Industry
Introduction
Forecasting is a technique used to predict the future by using numerical facts and previous experience to indicate the end of a given product in the market. The forecast is used applied in a different field and is mostly used for business during budgeting. However, this paper will focus on a case study of forecasting services in the Korean Film Market.
The Korean movie industry is one of the thriving industries in the Asian continent. The uniqueness of the Korean film success rates is predicted through a box office. This case study’s drive was to elaborate on how people can invest in motion pictures, which are considered a high-risk business, due to their reliance on the ratings from different levels. However, through the box office forecast models, the investor has been able to survive and profit from Korea’s film industry.
In this case, the forecasting model is developed from three aspects: screen-related information, word of mouth, and competition. According to Kim et al. (2017), this information provides the accuracy required to forecast a particular movie’s success in the industry. As a genre, ratings, nationality, and distribution of the films running concurrently with the target motion picture describe the competition. Simultaneously, the content posted on social media platforms provides both positive and negative word-of-mouth reviews. However, the forecast is based on few samples from these variables, selected by a genetic algorithm. This is based on the machine learning algorithms are trained to build forecasting models. However, to make it more effective, the forecasts are combined to enhance their accuracy.
The application of the box office forecast models on the Korean film industry shows that the forecasting accuracy in the early screening period can be improved by considering the competition variables. And word-of-mouth has a strong influence on the total box office forecasting model. Nevertheless, combining the two variables improves the forecasting performance significantly than when one of them is considered (Kim et al., 2017).
Studies have been conducted on the forecasting services of the box office, where the majority of these researches are categorized in three, one being the basis of the research subjects, which are identifying and investigating influential factors, or explanatory variables in forecast models, implementation of new forecast algorithms, and analysis of the effects of different forecast horizons. According to the authors, little has been done to systematically address all of these problems from a modeling perspective. In this case, the aim was to recreate a more accurate forecasting model by incorporating different model factors. This includes a well-defined and machine-leaning algorithm that is nonlinear regression-based (Kim et al., 2017).
The forecasting accuracy will be improved on the new model by inputting different variables from three different categories identified in the research. The variables category includes the screening information. The data to be considered on this variable category consists of the number of seats on the released date, previously used as a proxy for distribution power. The completion environment comes as the second category, where movies with overlapping screening periods are in a zero-sum competition for limited audiences. Hence the release scheme has a significant influence on the final box office score. The last variable category is word-of-mouth; the model will also use the nonlinear regression algorithm to improve the box office’s current forecasting accuracy (Kim et al., 2017).

In conclusion, the ultimate goal of the study, in this case, is to develop an efficient and more accurate forecasting model for the film industry, which will be available at the release date. This will be supported by applying machine learning technology. The algorithms will increase the box office’s performance, giving a perfect prediction to the investors, thus reducing the film industry’s perception of the high-risk investing sectors.

References
Kim, T., Hong, J., & Kang, P. (2017). Box office forecasting considering competitive environment and word-of-mouth in social networks: a Korean film market case study. Computational intelligence and neuroscience, 2017. https://www.google.com/url?sa=t&rct=j&q=&esrc=s&source=web&cd=&cad=rja&uact=8&ved=2ahUKEwj37_uzjdr6AhWHgf0HHWUWAYAQFnoECAsQAQ&url=https%3A%2F%2Fwww.hindawi.com%2Fjournals%2Fcin%2F2017%2F4315419%2F&usg=AOvVaw1PrEysNzJsIiVs3Da4TrYs