Abstract:

Concerning the limitations that the accuracy of prediction is low and the classification on box-office is not significant in application, this paper proposed a new model to predict box-revenue of movie, based on the movie market in reality. The algorithm could be summarized as follows. Firstly, the factors that affected the box and format of the output were determined. Secondly, these factors should be analyzed and quantified within [0, 1]. Then, the number of neurons was also determined, aiming to build up the architecture of the neural network according to input and output. The algorithm and procedure were improved before finishing the prediction model. Finally, the model was trained with denoised historical movie data, and the output of model was optimized to dispel the randomness so that the result could reflect box more reliably. The experimental results demonstrate that the model based on back propagation neural network algorithm performs better on prediction and classification (For the first five weeks, the average relative error is 43.2% while the average accuracy rate achieves 93.69%), so that it can provide a more comprehensive and reliable suggestion for publicity and risk assessment before the movie is on, which possesses a better application value and research prospect in the prediction field.

Key words: multiple layer back propagation neural network, prediction of movies&rsquo, box revenue, box classification, quantification of factor

摘要：

针对电影票房预测与分类的研究中存在预测精度不高、缺乏实际应用价值等缺陷，通过对中国电影票房市场的研究，提出一种基于反馈神经网络的电影票房预测模型。首先，确定电影票房的影响因素以及输出结果格式；其次，对这些影响因子进行定量分析和归一量化处理；再次，根据确定的输入和输出变量确定各个网络层次神经元数量，建立神经网络结构，改进神经网络预测的算法和流程，建立票房预测模型;最后，用经过去噪处理的电影历史票房数据对神经网络进行训练。针对神经网络波动性的特点，对预测模型的输出结果进行改进之后，输出结果既能更可靠地反映电影在上映期间的票房收入，又能指出电影票房的波动范围。仿真结果表明，对于实验中的192部电影，基于神经网络算法的预测模型有较好的预测和分类性能(前5周票房的平均相对误差为43.2%，平均分类正确率可达93.69%)，能够为电影在上映前的投资、宣传以及风险评估提供较全面、可靠的参考方案，在预测分类领域具有较好的应用价值和研究前景。

关键词: 多层反馈神经网络, 电影票房预测, 票房分类, 影响因素量化