共查询到19条相似文献,搜索用时 171 毫秒
1.
2.
在零售商的角度,通常希望推荐系统的推荐产品能使商家的收益最大化。在以期望收益最大化为目标的产品组合优化模型中,商品效用是必不可少的参数。论文主要探究推荐系统中商品效用的估计方法,通过评估由商品效用计算得到的商品被点击概率,来验证效用估计的准确性。通过数值试验,将单值排序模型预估的点击概率与通过MNL模型估计商品效用计算的点击概率进行对比,结果证明MNL模型估计的商品效用具备与单值排序模型相当的准确率。此外,论文进一步构建了神经网络模型估计商品效用,并且另外构建了一个直接计算商品点击概率的attention选择模型作为对比。结果证明使用神经网络模型代替MNL来估计商品效用,能够更进一步提升效用预估的准确性。 相似文献
3.
4.
协作过滤是应用最为广泛的推荐技术,通常提供预测评分作为推荐。提出一种新的协作过滤算法,采用概率形式.即预测用户喜欢商品的概率来推荐。算法采用基于用户的思路,扩展最近邻算法,通过训练建立预测值和概率形式之间的映射模型,考察相似用户的评价提供概率形式的推荐。实验结果表明该算法能够提供比较准确的预测。 相似文献
5.
6.
7.
随着全球信息技术的迅猛发展,信息数据呈现出爆发式增长的趋势,如何从海量的数据中找出有价值的信息,是一个迫切需要解决的问题.推荐系统是解决这一问题的有效途径,而如何把深度学习这项技术融入推荐系统,是目前的研究热点.文章分析了传统的推荐系统存在的问题,提出了相应的解决方法和对策,使系统模型与用户的需求结合更加紧密,用户的满... 相似文献
8.
9.
协同过滤算法是目前个性化推荐系统中应用最成功的推荐算法之一。目前协同过滤构建的用户-项目矩阵,一般是按用户对所有项目的评分构建,却没有考虑项目之间的分类情况,导致寻找的邻居集合可能不是最近邻居集合。针对此问题,本文提出基于项目聚类和评分预测的协同过滤推荐算法,该算法首先按商品聚类,将大矩阵按聚类的商品来进行子矩阵的计算,在子矩阵里进行兴趣度的测量,最后将在所有区域相似用户的推荐项目合并,成为该用户的最后推荐结果。实验证明新算法能够提高协同过滤推荐系统的推荐质量。 相似文献
10.
本文研究多产品移动通信业务以及非线性定价条件下的消费者需求理论,并利用话单层级的用户消费数据,建立离散选择结构计量模型,并对用户资费选择行为与个人属性、资费属性和换网行为之间的关系进行研究,最后利用估计出的需求结构参数,就资费优化对企业收入和用户资费选择概率的影响进行分析。 相似文献
11.
《International Journal of Forecasting》2022,38(1):240-252
This study evaluates a wide range of machine learning techniques such as deep learning, boosting, and support vector regression to predict the collection rate of more than 65,000 defaulted consumer credits from the telecommunications sector that were bought by a German third-party company. Weighted performance measures were defined based on the value of exposure at default for comparing collection rate models. The approach proposed in this paper is useful for a third-party company in managing the risk of a portfolio of defaulted credit that it purchases. The main finding is that one of the machine learning models we investigate, the deep learning model, performs significantly better out-of-sample than all other methods that can be used by an acquirer of defaulted credits based on weighted-performance measures. By using unweighted performance measures, deep learning and boosting perform similarly. Moreover, we find that using a training set with a larger proportion of the dataset does not improve prediction accuracy significantly when deep learning is used. The general conclusion is that deep learning is a potentially performance-enhancing tool for credit risk management. 相似文献
12.
This paper proposes a model of two-party representative democracy on a single-dimensional political space, in which voters choose their parties in order to influence the parties’ choices of representative. After two candidates are selected as the median of each party’s support group, Nature determines the candidates’ relative likability (valence). Based on the candidates’ political positions and relative likability, voters vote for the preferable candidate without being tied to their party’s choice. We show that (1) there exists a nontrivial equilibrium under natural conditions, and (2) the equilibrium party border and the ex ante probabilities of the two-party candidates winning are sensitive to the distribution of voters. In particular, we show that if a party has a more concentrated subgroup, then the party tends to alienate its centrally located voters, and the party’s probability of winning the final election is reduced. Even if voter distribution is symmetric, an extremist party (from either side) can emerge as voters become more politically divided. 相似文献
13.
Probability matching occurs when an action is chosen with a frequency equivalent to the probability of that action being the best choice. This sub-optimal behavior has been reported repeatedly by psychologists and experimental economists. We provide an evolutionary foundation for this phenomenon by showing that learning by reinforcement can lead to probability matching and, if the learning occurs sufficiently slowly, probability matching does not only occur in choice frequencies but also in choice probabilities. Our results are completed by proving that there exists no quasi-linear reinforcement learning specification such that the behavior is optimal for all environments where counterfactuals are observed. 相似文献
14.
A regression discontinuity (RD) research design is appropriate for program evaluation problems in which treatment status (or the probability of treatment) depends on whether an observed covariate exceeds a fixed threshold. In many applications the treatment-determining covariate is discrete. This makes it impossible to compare outcomes for observations “just above” and “just below” the treatment threshold, and requires the researcher to choose a functional form for the relationship between the treatment variable and the outcomes of interest. We propose a simple econometric procedure to account for uncertainty in the choice of functional form for RD designs with discrete support. In particular, we model deviations of the true regression function from a given approximating function—the specification errors—as random. Conventional standard errors ignore the group structure induced by specification errors and tend to overstate the precision of the estimated program impacts. The proposed inference procedure that allows for specification error also has a natural interpretation within a Bayesian framework. 相似文献
15.
Ricardo P. Masini Marcelo C. Medeiros Eduardo F. Mendes 《Journal of economic surveys》2023,37(1):76-111
In this paper, we survey the most recent advances in supervised machine learning (ML) and high-dimensional models for time-series forecasting. We consider both linear and nonlinear alternatives. Among the linear methods, we pay special attention to penalized regressions and ensemble of models. The nonlinear methods considered in the paper include shallow and deep neural networks, in their feedforward and recurrent versions, and tree-based methods, such as random forests and boosted trees. We also consider ensemble and hybrid models by combining ingredients from different alternatives. Tests for superior predictive ability are briefly reviewed. Finally, we discuss application of ML in economics and finance and provide an illustration with high-frequency financial data. 相似文献
16.
The study of behavioral intention for mobile commerce: via integrated model of TAM and TTF 总被引:2,自引:0,他引:2
Mobile commerce systems allow customers to purchase products over the Internet without using a pc. It also creates a new mobile business model and change e-commerce paradigms, having an especially significant effect on the medical and insurance industries. Furthermore, the real estate industry is increasing in the booming market, but tends to become overheated. Thus, some innovative techniques (such as mobile commerce) were adopted by estate agent to enhance their competitive advantage. Consequently, identifying the match between mobile commerce technique and individual performance is a valuable focus of research. In fact, technology acceptance model (TAM) is a well-known theory regarding the adoption of information technology (IT), but ignores the focus on evaluating IT; meanwhile, the task-technology fit (TTF) model takes a directly rational approach by assuming that users choose to use IT that provides benefits but does not consider about users’ beliefs and attitude towards IT. Therefore, this study examined an integrated model of TAM and TTF that provided additional explanatory power via structural equation modeling. Analytical results confirm that the integrated model provides greater explanatory power than either TAM or TTF alone. Furthermore, several practical implications and recommendations are also discussed below. 相似文献
17.
We are concerned with solidarity and a Doeblin decomposition for a class of non-Markovian discrete parameter stochastic processes. Since any such process is associated with a certain general Markov chain whose transition probability function has a special form, we use the theory of Markov chains with continuous components to this particular chain in order to get properties of the non-Markovian process. We illustrate our results on a model closely related to learning theory. 相似文献
18.
《International Journal of Forecasting》2019,35(2):741-755
The introduction of artificial intelligence has given us the ability to build predictive systems with unprecedented accuracy. Machine learning is being used in virtually all areas in one way or another, due to its extreme effectiveness. One such area where predictive systems have gained a lot of popularity is the prediction of football match results. This paper demonstrates our work on the building of a generalized predictive model for predicting the results of the English Premier League. Using feature engineering and exploratory data analysis, we create a feature set for determining the most important factors for predicting the results of a football match, and consequently create a highly accurate predictive system using machine learning. We demonstrate the strong dependence of our models’ performances on important features. Our best model using gradient boosting achieved a performance of 0.2156 on the ranked probability score (RPS) metric for game weeks 6 to 38 for the English Premier League aggregated over two seasons (2014–2015 and 2015–2016), whereas the betting organizations that we consider (Bet365 and Pinnacle Sports) obtained an RPS value of 0.2012 for the same period. Since a lower RPS value represents a higher predictive accuracy, our model was not able to outperform the bookmaker’s predictions, despite obtaining promising results. 相似文献
19.
Dynamic discrete choice panel data models have received a great deal of attention. In those models, the dynamics is usually handled by including the lagged outcome as an explanatory variable. In this paper we consider an alternative model in which the dynamics is handled by using the duration in the current state as a covariate. We propose estimators that allow for group-specific effect in parametric and semiparametric versions of the model. The proposed method is illustrated by an empirical analysis of job durations allowing for firm-level effects. 相似文献