MAKİNE ÖĞRENMESİ ALGORİTMALARI KULLANARAK GİŞE HASILATININ TAHMİNİ

Yıl 2017, Cilt: 3 Sayı: 2, 130 - 143, 20.12.2017

Özge Hüsniye Namlı , Tuncay Özcan

Öz

Yeni
efektler ve 3 boyutlu çekimler gibi güncel gelişmeler film endüstrisindeki
rekabeti arttırmaktadır. Film endüstrisindeki pahalı ve riskli yatırımlar için
üretim öncesi analizler giderek önem kazanmaktadır. Bu noktada, gişe hasılatı
tahmini önemli bir araştırma konusu olmuştur. Bu bağlamda, bu çalışma gişe
hasılatı tahmini için makine öğrenmesi algoritmaları kullanarak bir yaklaşım
sunmayı amaçlamaktadır. Geleneksel yapay zeka metotlarından yapay sinir ağları
ve destek vektör makineleri algoritmaları, karar ağaçları algoritmalarından
rastgele ağaç, rastgele orman ve C4.5 algoritmaları kullanılmıştır. Daha sonra,
bu algoritmalar ile topluluk algoritmalarından torbalama algoritması kullanılarak
melez bir model önerilmiştir. Tahmin modelleri doğru sınıflandırma yüzdesi, kappa
istatistiği, ROC alanı ile değerlendirilmiştir. Sayısal sonuçlar, rastgele
orman-torbalama ve yapay sinir ağları-torbalama melez metotlarının tüm modeller
arasında en iyi performansa sahip olduğunu göstermektedir. 

Anahtar Kelimeler

: Gişe hasılatı, Yapay sinir ağları, Destek vektör makineleri, Karar ağaçları, Makine öğrenmesi

FORECASTING OF BOX OFFICE REVENUE USING MACHINE LEARNING ALGORITHMS

Öz

Current developments such as new effects and 3D
shootings increase the competition in the movie industry. Pre-production
analyzes are becoming more important for the expensive and risky investments in
the movie industry. At this point, the prediction of the box office revenue has
become an important research issue. In this context, this study aims to present
an approach using machine learning algorithms for box-office revenue prediction.
Artificial neural networks and support vector machines algorithms as traditional
artificial intelligence methods and random trees, random forests and C4.5
algorithms as decision tree algorithms are used. Later, a hybrid model is proposed
using these algorithms and the bagging algorithm from the ensemble algorithm. Prediction
models are evaluated with the percentage of correct classification, kappa
statistics and ROC area. Numerical results show that Random forest-bagging and
artificial neural networks-bagging hybrid methods have the best performance
among all models.

Anahtar Kelimeler

Box-office Revenue, Artificial Neural Networks, Support Vector Machines, Decision Trees, Machine Learning

Kaynakça

• Abou-Nasr, M., Lessmann, S., Stahlbock, R., & Weiss, G. M. (Eds.). (2014). Real world data mining applications (Vol. 17). Springer.
• Aggarwal, C. C. (2015). Data mining: the textbook. Springer.
• Akçetin, E., & Çelik, U. (2014). İstenmeyen Elektronik Posta (Spam) Tespitinde Karar Ağacı Algoritmalarının Performans Kıyaslaması. Journal of Internet Applications & Management/İnternet Uygulamaları ve Yönetimi Dergisi, 5(2).
• Breiman, L. (1996). Bagging predictors. Machine learning, 24(2), 123-140.
• Breiman, L. (2001). Random forests. Machine learning, 45(1), 5-32.
• Castillo, P. A., Mora, A. M., Faris, H., Merelo, J. J., García-Sánchez, P., Fernández-Ares, A. J., … García-Arenas, M. I. (2016). Applying Computational Intelligence Methods for Predicting the Sales of Newly Published Books in a Real Editorial Business Management Environment. Knowledge-Based Systems, 115, 133–151.
• Chou, J. S., Tsai, C. F., Pham, A. D., & Lu, Y. H. (2014). Machine learning in concrete strength simulations: Multi-nation data analytics. Construction and Building Materials, 73, 771–780.
• Cichosz, P. (2014). Data Mining Algorithms: Explained Using R. John Wiley & Sons.
• Delen, D., Sharda, R., & Kumar, P. (2007). Movie forecast Guru: A Web-based DSS for Hollywood managers. Decision Support Systems, 43(4), 1151–1170.
• Erdal, H. I., Karakurt, O., & Namli, E. (2013). High performance concrete compressive strength forecasting using ensemble models based on discrete wavelet transform. Engineering Applications of Artificial Intelligence, 26(4), 1246–1254.
• Ghiassi, M., Lio, D., & Moon, B. (2015). Pre-production forecasting of movie revenues with a dynamic artificial neural network. Expert Systems with Applications, 42(6), 3176–3193.
• Han, J. & Kamber, M. (2006). Data Mining: Concepts and Techniques, San Francisco: Morgan Kaufmann Publishers.
• Hsu, C.-W., Chang, C.-C., & Lin, C.-J. (2003). A practical guide to support vector classification. Department of Computer Science, National Taiwan University.
• Hur, M., Kang, P., & Cho, S. (2016). Box-office forecasting based on sentiments of movie reviews and Independent subspace method. Information Sciences, 372, 608–624.
• Kalmegh, S. (2015). Analysis of WEKA Data Mining Algorithm REPTree, Simple Cart and RandomTree for Classification of Indian News. International Journal of Innovative Science, Engineering & Technology, 2(2), 438-446.
• Quinlan, J. R. (1993). C4. 5: Programs for machine learning. California: Morgan Kauffmann Publishers.
• Rokach, L., & Maimon, O. (2014). Data mining with decision trees: theory and applications. World scientific.
• Sasaki, Y. (2007). The truth of the F-measure. Teach Tutor mater, 1(5).
• Sharda, R., & Delen, D. (2006). Predicting box-office success of motion pictures with neural networks. Expert Systems with Applications.
• Tu, J. V. (1996). Advantages and disadvantages of using artificial neural networks versus logistic regression for predicting medical outcomes. Journal of clinical epidemiology, 49(11), 1225-1231.
• Witten, I. H., Frank, E., & Hall, M. A., (2011). Data Mining: Practical Machine Learning Tools and Techniques. Morgan Kaufmann.
• Wu, T. K., Huang, S. C., & Meng, Y. R. (2008). Evaluation of ANN and SVM classifiers as predictors to the diagnosis of students with learning disabilities. Expert Systems with Applications, 34(3), 1846-1856.
• Zhang, L., Luo, J., & Yang, S. (2009). Forecasting box office revenue of movies with BP neural network. Expert Systems with Applications, 36(3 PART 2), 6580–6587.