Predicting box-office success of motion pictures with neural networks

Predicting box-office receipts of a particular motion picture has intrigued many scholars and industry leaders as a difficult and challenging problem. In this study, the use of neural networks in predicting the financial performance of a movie at the box-office before its theatrical release is explored. In our model, the forecasting problem is converted into a classification problem-rather than forecasting the point estimate of box-office receipts, a movie based on its box-office receipts in one of nine categories is classified, ranging from a ‘flop’ to a ‘blockbuster.’ Because our model is designed to predict the expected revenue range of a movie before its theatrical release, it can be used as a powerful decision aid by studios, distributors, and exhibitors. Our prediction results is presented using two performance measures: average percent success rate of classifying a movie's success exactly, or within one class of its actual performance. Comparison of our neural network to models proposed in the recent literature as well as other statistical techniques using a 10-fold cross validation methodology shows that the neural networks do a much better job of predicting in this setting.     

Predicting movie success with machine learning techniques: ways to improve accuracy

Previous studies on predicting the box-office performance of a movie using machine learning techniques have shown practical levels of predictive accuracy. Their works are technically- and methodologically-oriented, focusing mainly on what algorithms are better at predicting the movie performance. However, the accuracy of prediction model can also be elevated by taking other perspectives such as introducing unexplored features that might be related to the prediction of the outcomes. In this paper, we examine multiple approaches to improve the performance of the prediction model. First, we develop and add a new feature derived from the theory of transmedia storytelling. Such theory-driven feature selection not only increases the forecast accuracy, but also enhances the interpretability of a prediction model. Second, we use an ensemble approach, which has rarely been adopted in the research on predicting box-office performance. As a result, the proposed model, Cinema Ensemble Model (CEM), outperforms the prediction models from the past studies that use machine learning algorithms. We suggest that CEM can be extensively used for industrial experts as a powerful tool for improving decision-making process.     

基于神经网络的电影票房预测建模

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。     

贝叶斯网模型的学习、推理和应用

近年来在人工智能领域,不确定性问题一直成为人们关注和研究的焦点。贝叶斯网是用来表示不确定变量集合联合概率分布的图形模式,它反映了变量间潜在的依赖关系。使用贝叶斯网建模已成为解决许多不确定性问题的强有力工具。基于国内外最新的研究成果对贝叶斯网模型的学习、推理和应用情况进行了综述,并对未来的发展方向进行了展望。     

Bayesian Belief Network-based approach for diagnostics and prognostics of semiconductor manufacturing systems

Semiconductor manufacturing is a complex process in that it requires different types of equipments (also referred to as tools in semiconductor industry) with various control variables under monitoring. As the number of sensors grows, a huge amount of data are collected from the production; and yet, the relations among these control variables and their effects on finished wafer are to be fully understood for both equipment monitoring and quality assurance. Meanwhile, as the wafer goes through multiple periods with different recipes, failure that occurs during the process can both cause tremendous loss to manufacturer and compromise product quality. Therefore, occurred failure should be detected as soon as possible, and root cause need to be identified so that corrections can be made in time to avoid further loss. In this paper, we propose to apply Bayesian Belief Network (BBN) to investigate the causal relationship among process variables on the tool and evaluate their influence on wafer quality. By building BBN models at different periods of the process, the causal relation between control parameters, and their influence on wafer can be both qualitatively indicated by the network structure and quantitatively measured by the conditional probabilities in the model. In addition, with the BBN probability propagation, one can diagnose root causes when bad wafer is produced; or predict the wafer quality when abnormal is observed during the process. Our tests on a Chemical Vapor Deposition (CVD) tool show that the BBN model achieves high classification rate for wafer quality, and accurately identifies problematic sensors when bad wafer is found.     

Bayesian networks based rare event prediction with sensor data

A Bayesian network is a powerful graphical model. It is advantageous for real-world data analysis and finding relations among variables. Knowledge presentation and rule generation, based on a Bayesian approach, have been studied and reported in many research papers across various fields. Since a Bayesian network has both causal and probabilistic semantics, it is regarded as an ideal representation to combine background knowledge and real data. Rare event predictions have been performed using several methods, but remain a challenge. We design and implement a Bayesian network model to forecast daily ozone states. We evaluate the proposed Bayesian network model, comparing it to traditional decision tree models, to examine its utility.     

A method of sensor fault detection and identification

A method of Bayesian belief network (BBN)-based sensor fault detection and identification is presented. It is applicable to processes operating in transient or at steady-state. A single-sensor BBN model with adaptable nodes is used to handle cases in which process is in transient. The single-sensor BBN model is used as a building block to develop a multi-stage BBN model for all sensors in the process under consideration. In the context of BBN, conditional probability data represents correlation between process measurable variables. For a multi-stage BBN model, the conditional probability data should be available at each time instant during transient periods. This requires generating and processing a massive data bank that reduces computational efficiency. This paper presents a method that reduces the size of the required conditional probability data to one set. The method improves the computational efficiency without sacrificing detection and identification effectiveness. It is applicable to model- and data-driven techniques of generating conditional probability data. Therefore, there is no limitation on the source of process information. Through real-time operation and simulation of two processes, the application and performance of the proposed BBN method are shown. Detection and identification of different sensor fault types (bias, drift and noise) are presented. For one process, a first-principles model is used to generate the conditional probability data, while for the other, real-time process data (measurements) are used.     

基于加权K-Means和局部BPNN的票房预测模型

电影作为典型的短周期、体验型产品,其票房收益受众多因素的共同影响,因此对其票房进行预测较为困难.本文主要构建了一种基于加权K-均值以及局部BP神经网络（BPNN）的票房预测模型对目前的票房预测模型存在的不足进行改进,从而提高票房预测的精度：（1）构建基于随机森林的影响因素影响力测量模型,并以此为依据对票房影响因素进行筛选,以此来简化后续预测模型的输入;（2）考虑到不同影响因素对票房的影响力不同的现实情况,为了解决以往研究中对影响因素权重平均分配的问题,本文构建了基于加权K-均值和局部BP神经网络的票房预测模型,以因素影响力为依据对样本数据进行加权的K-均值聚类,并基于子样本构建局部BP神经网络模型进行票房预测.实验证明,本文所构建的模型平均绝对百分比误差（MAPE）为8.49%,低于对比实验的10.39%,可以看出本文构建的基于加权K-均值以及局部BP神经网络的票房预测模型的预测结果要优于对比模型的预测结果.     

DCFM：基于深度学习的混合推荐模型

传统推荐算法大多都仅考虑用户-商品评级信息来进行推荐,这种忽略了用户属性和商品属性信息的推荐模型准确率不高。因子分解机可在数据稀疏情况下挖掘用户与商品的关联关系,交叉网络可挖掘属性特征与其高阶特征的线性组合关系,以及深度神经网络有效识别高阶非线性关联关系,基于三种模型的优势,提出了一种基于深度学习的混合推荐模型（Deep and Cross Factorization Machine,DCFM）。三部分并联组合,共享输入层,各部分结果线性组合后作为模型整体输出。通过在MovieLens电影数据集上仿真实验,并与因子分解机（FM）、深度因子分解机（DeepFM）、深度交叉网络（DCN）模型做比较,结果证明该模型在准确率、F1-Score和AUC值上均得到了提高和改善。     

A Bayesian belief network modelling of household factors influencing the risk of malaria: A study of parasitaemia in children under five years of age in sub-Saharan Africa

Studies that focus on integrated modelling of household factors and the risk for malaria parasitaemia among children in sub-Saharan Africa (SSA) are scarce. By using Malaria Indicator Survey, Demographic Health Survey, AIDS Indicator Survey datasets, expert knowledge and existing literature on malaria, a Bayesian belief network (BBN) model was developed to bridge this gap. Results of sensitivity analysis indicate that drinking water sources, household wealth, nature of toilet facilities, mother's educational attainment, types of main wall, and roofing materials, were significant factors causing the largest entropy reduction in malaria parasitaemia. Cattle rearing and residence type had less influence. Model accuracy was 86.39% with an area under the receiver-operating characteristic curve of 0.82. The model's spherical payoff was 0.80 with the logarithmic and quadratic losses of 0.53 and 0.35 respectively indicating a strong predictive power. The study demonstrated how BBN modelling can be used in determining key interventions for malaria control.     

基于多特征融合的电影推荐系统

协同过滤算法（CF）根据用户-物品的评分矩阵做推荐，未考虑物品自身属性。本文将MovieLens数据集上的电影属性，作为影响推荐结果的因素，融合电影的简介、评论、评分、导演和演员等多种因素，进行推荐。使用CNN（卷积神经网络）和Word2Vec（Word to Vector,词向量模型）处理电影简介；使用AFINN（Finn rup Nielsen情感词典）处理评论，并对结果进行映射；对导演和演员数据进行建模，得到该因素下的预测评分，最后将各因素下的结果进行加权融合，通过调整权重，得到最佳效果。经验证，该方法的推荐性能优于传统的CF算法。     

基于改进贝叶斯网络的健康大数据分类模型

贝叶斯网络是数据挖掘领域的研究热点,它是一种确定事物间不确定性依赖关系的有效工具。本文研究传统贝叶斯网络结构学习算法的优点和不足,并针对原算法的不足之处提出了改进。将改进后的算法应用于健康大数据集上,确定了数据集中各个健康属性之间的依赖关系,建立了相关属性依赖关系的网络结构。最终运用该网络结构对数据集中的数据进行自动分类。实验结果表明,本文基于贝叶斯网络建立的健康大数据分类模型具有良好的性能,实现了预期效果。     

基于课程学习思想的目标检测增强算法

目标检测算法性能优劣既依赖于数据集样本分布,又依赖于特征提取网络设计.从这2点出发,首先通过分析COCO 2017数据集各尺度目标属性分布,探索了数据集固有的导致小目标检测准确率偏低的潜在因素,据此提出CP模块,该模块以离线方式调整数据集小目标分布,一方面对包含小目标图片进行上采样,另一方面对图片内小目标进行复制粘贴....     

Validation of a bayesian belief network representation for posterior probability calculations on national crime victimization survey

This paper presents an effort to induce a Bayesian belief network (BBN) from crime data, namely the national crime victimization survey (NCVS). This BBN defines a joint probability distribution over a set of variables that were employed to record a set of crime incidents, with particular focus on characteristics of the victim. The goals are to generate a BBN to capture how characteristics of crime incidents are related to one another, and to make this information available to domain specialists. The novelty associated with the study reported in this paper lies in the use of a Bayesian network to represent a complex data set to non-experts in a way that facilitates automated analysis. Validation of the BBN’s ability to approximate the joint probability distribution over the set of variables entailed in the NCVS data set is accomplished through a variety of sources including mathematical techniques and human experts for appropriate triangulation. Validation results indicate that the BBN induced from the NCVS data set is a good joint probability model for the set of attributes in the domain, and accordingly can serve as an effective query tool.

An evolutionary Bayesian belief network methodology for optimum management of groundwater contamination

An integrated methodology, based on Bayesian belief network (BBN) and evolutionary multi-objective optimization (EMO), is proposed for combining available evidence to help water managers evaluate implications, including costs and benefits of alternative actions, and suggest best decision pathways under uncertainty. A Bayesian belief network is a probabilistic graphical model that represents a set of variables and their probabilistic relationships, which also captures historical information about these dependencies. In complex applications where the task of defining the network could be difficult, the proposed methodology can be used in validation of the network structure and the parameters of the probabilistic relationship. Furthermore, in decision problems where it is difficult to choose appropriate combinations of interventions, the states of key variables under the full range of management options cannot be analyzed using a Bayesian belief network alone as a decision support tool. The proposed optimization method is used to deal with complexity in learning about actions and probabilities and also to perform inference. The optimization algorithm generates the state variable values which are fed into the Bayesian belief network. It is possible then to calculate the probabilities for all nodes in the network (belief propagation). Once the probabilities of all the linked nodes have been updated, the objective function values are returned to the optimization tool and the process is repeated. The proposed integrated methodology can help in dealing with uncertainties in decision making pertaining to human behavior. It also eliminates the shortcoming of Bayesian belief networks in introducing boundary constraints on probability of state values of the variables. The effectiveness of the proposed methodology is examined in optimum management of groundwater contamination risks for a well field capture zone outside Copenhagen city.     

Neural networks for construction project success

Being able to identify key attributes for successful project performance is of paramount importance to project owners, contractors, and designers. Understanding these key factors can help in the efficient execution of a construction project. This paper identifies key project management attributes associated with achieving successful budget performance using a neural network approach. Neural network models were developed using field data comprising potential determinants of construction project success. Altogether eight key project management factors were identified: (1) number of organizational levels between the project manager and craft workers; (2) amount of detailed design completed at the start of construction; (3) number of control meetings during the construction phase; (4) number of budget updates; (5) implementation of a constructability program; (6) team turnover; (7) amount of money expended on controlling the project; (8) the project manager's technical experience. The final model, after sufficient training, can also be used as a predictive tool to forecast budget performance of a construction project. This approach allows the budget performance model to be built even though the functional interrelationships between inputs and output are not clearly defined. The model also performs reasonably well with incomplete information of the inputs.     

A probabilistic model for predicting software development effort

Recently, Bayesian probabilistic models have been used for predicting software development effort. One of the reasons for the interest in the use of Bayesian probabilistic models, when compared to traditional point forecast estimation models, is that Bayesian models provide tools for risk estimation and allow decision-makers to combine historical data with subjective expert estimates. In this paper, we use a Bayesian network model and illustrate how a belief updating procedure can be used to incorporate decision-making risks. We develop a causal model from the literature and, using a data set of 33 real-world software projects, we illustrate how decision-making risks can be incorporated in the Bayesian networks. We compare the predictive performance of the Bayesian model with popular nonparametric neural-network and regression tree forecasting models and show that the Bayesian model is a competitive model for forecasting software development effort.     

A Bayesian belief network analysis of factors influencing wildfire occurrence in Swaziland

The impacts of wildfires on ecosystems and the factors contributing to their occurrence are increasingly receiving global attention. Advances in satellite remote sensing and information technology provide an opportunity to study these complex interrelationships. A Bayesian belief network (BBN) model was developed from a set of 12 biotic, abiotic and human variables to determine factors that influence wildfire activity in Swaziland using wildfire data from the Terra and Aqua satellites' Moderate Resolution Imaging Spectroradiometer (MODIS) for the period 2001–2007. These were geospatially integrated in the geographic information system (GIS) software ArcView and input into the software Netica for BBN analyses. Land cover, elevation, and climate (mean annual rainfall and mean annual temperature) were found to be strong predictors of wildfire occurrence, while aspect had the least influence on the wildfire occurrence. The model had a high predictive accuracy with an error rate of 9.62%, and an area under the receiver-operating characteristic (ROC) curve of 0.961. The study demonstrates how domain or field knowledge and limited empirical and GIS data can be combined within a BBN model to assist in determining key fire management interventions and lays the foundation for the future development of advanced and dynamic models.     

Time-delay neural networks for time series prediction: an application to the monthly wholesale price of oilseeds in India

Agricultural price forecasting is one of the challenging areas of time series forecasting. The feed-forward time-delay neural network (TDNN) is one of the promising and potential methods for time series prediction. However, empirical evaluations of TDNN with autoregressive integrated moving average (ARIMA) model often yield mixed results in terms of the superiority in forecasting performance. In this paper, the price forecasting capabilities of TDNN model, which can model nonlinear relationship, are compared with ARIMA model using monthly wholesale price series of oilseed crops traded in different markets in India. Most earlier studies of forecast accuracy for TDNN versus ARIMA do not consider pretesting for nonlinearity. This study shows that the nonlinearity test of price series provides reliable guide to post-sample forecast accuracy for neural network model. The TDNN model in general provides better forecast accuracy in terms of conventional root mean square error values as compared to ARIMA model for nonlinear patterns. The study also reveals that the neural network models have clear advantage over linear models for predicting the direction of monthly price change for different series. Such direction of change forecasts is particularly important in economics for capturing the business cycle movements relating to the turning points.     

基于本体特征的影评细粒度情感分类

针对中文影评情感分类中缺少特征属性及情感强度层面的粒度划分问题,提出一种基于本体特征的细粒度情感分类模型。首先,利用词频逆文档频率（TF-IDF）和TextRank算法提取电影特征,构建本体概念模型。其次,将电影特征属性和普鲁契克多维度情绪模型与双向长短时记忆网络（Bi-LSTM）融合,构建了在特征粒度层面和八分类情感强度下的细粒度情感分类模型。实验中,本体特征分析表明：观影人对故事属性关注度最高,继而是题材、人物、场景、导演等特征;模型性能分析表明：基于特征粒度和八分类情感强度,与应用情感词典、机器学习、Bi-LSTM网络算法在整体粒度和三分类情感强度层面的其他5个分类模型相比,该模型不仅有较高的F1值（0.93）,而且还能提供观影人对电影属性的情感偏好和情感强度参考,实现了中文影评更细粒度的情感分类。