#TITLE_ALTERNATIVE#

• Main Author: HIDAYAT (NIM : 10106022); Pembimbing : Dr. Novriana Sumarti; Khreshna I.A. Syuhada, Ph.D, RAFKI
• Format: Final Project
• Language: Indonesia
• Online Access: https://digilib.itb.ac.id/gdl/view/16894
• Institution: Institut Teknologi Bandung

In the United States, most of Hollywood movies open in theaters for the first time on a weekend, as the majority of audiences watch movies during the weekends (Friday, Saturday, and Sunday). The weekend box office revenue therefore accounts for a major part of the total weekly box office revenue. In this final project, extreme value theory is used to model the U.S. weekend box office returns, using weekly data for the period January 7, 2000 to December 27, 2009. The Peak over Threshold and Maximum Likelihood methods are used to estimate the parameters of generalized Pareto Distribution, a distribution that is employed to model the extreme values of weekend box office returns for both extreme positive and negative. Risk Measures (Value at Risk and Expected Shortfall) are also used to obtain the effects of extreme values on film industry. Data analysis shows that the tails of the distributions (the extremes) are able to model for both positive and negative returns satisfactorily with the generalized Pareto distribution. The estimation of Value at Risk and Expected Shortfall indicate that, with probability 1%, the revenue increase from one weekend to the next could exceed 73.50%, and when it does, the average increase is 87.88%. Also, with the same probability, box office revenue could drop 68.57% from one weekend to the next, and that when it does the average fall is 71.77%. Risk Measures imply that, given the same amount of investment, the possibility of loss for an investment in the movie industry is relatively lower than the possibility of gain.