Search results

Statistical methods of spatial analysis are often successful at either prediction or explanation, but not necessarily both. In a recent paper, Dearmon and Smith (2016) showed that by combining Gaussian Process Regression (GPR) with Bayesian Model Averaging (BMA), a modeling framework could be developed in which both needs are addressed. In particular, the smoothness properties of GPR together with the robustness of BMA allow local spatial analyses of individual variable effects that yield remarkably stable results. However, this GPR-BMA approach is not without its limitations. In particular, the standard (isotropic) covariance kernel of GPR treats all explanatory variables in a symmetric way that limits the analysis of their individual effects. Here we extend this approach by introducing a mixture of kernels (both isotropic and anisotropic) which allow different length scales for each variable. To do so in a computationally efficient manner, we also explore a number of Bayes-factor approximations that avoid the need for costly reversible-jump Monte Carlo methods.

To demonstrate the effectiveness of this Variable Length Scale (VLS) model in terms of both predictions and local marginal analyses, we employ selected simulations to compare VLS with Geographically Weighted Regression (GWR), which is currently the most popular method for such spatial modeling. In addition, we employ the classical Boston Housing data to compare VLS not only with GWR but also with other well-known spatial regression models that have been applied to this same data. Our main results are to show that VLS not only compares favorably with spatial regression at the aggregate level but is also far more accurate than GWR at the local level.

Multiple linear regression (MLR) is a commonly used statistical technique to predict future values. In this paper, we examine the situation in which a given time series dataset contains numerous observations of important predictor variables that can effectively be classified into groups based on their values. In such situations, cluster analysis is often employed to improve the MLR models predictive accuracy, usually by creating separate regressions for each cluster. We introduce a novel approach in which we use the clusters and cluster centroids as input data for the predictor variables to improve the predictive accuracy of the MLR model. We illustrate and test this approach with a real dataset on fleet maintenance.

This article reviews the quantitative marketing literature on artificial intelligence (AI) through an economics lens. We apply the framework in Prediction Machines: The Simple Economics of Artificial Intelligence to systematically categorize 96 research papers on AI in marketing academia into five levels of impact, which are prediction, decision, tool, strategy, and society. For each paper, we further identify each individual component of a task, the research question, the AI model used, and the broad decision type. Overall, we find there are fewer marketing papers focusing on strategy and society, and accordingly, we discuss future research opportunities in those areas.

We report an experiment conducted to gain insight into factors that may affect revenues in English auctions and lotteries, two commonly used charity fund-raising formats. In particular, we examine how changes in the marginal per capita return (MPCR) from the public component of bidding, and how changes in the distribution of values affect the revenue properties of each format. Although we observe some predicted comparative static effects, the dominant result is that lottery revenues uniformly exceed English auction revenues. The similarity of lottery and English auction bids across sales formats appears to drive the excess lottery revenues.

The purpose of this paper is to improve the information quality of bankruptcy prediction models proposed in the literature by building prediction intervals around the point estimates generated by these models and to determine if the use of the prediction intervals in conjunction with the point estimated yields an improvement in predictive accuracy over traditional models. The authors calculated the point estimates and prediction intervals for a sample of firms from 1991 to 2008. The point estimates and prediction intervals were used in concert to classify firms as bankrupt or non-bankrupt. The accuracy of the tested technique was compared to that of a traditional bankruptcy prediction model. The results indicate that the use of upper and lower bounds in concert with the point estimates yield an improvement in the predictive ability of bankruptcy prediction models. The improvements in overall prediction accuracy and non-bankrupt firm prediction accuracy are statistically significant at the 0.01 level. The authors present a technique that (1) provides a more complete picture of the firm’s status, (2) is derived from multiple forms of evidence, (3) uses a predictive interval technique that is easily repeated, (4) can be generated in a timely manner, (5) can be applied to other bankruptcy prediction models in the literature, and (6) is statistically significantly more accurate than traditional point estimate techniques. The current research is the first known study to use the combination of point estimates and prediction intervals to in bankruptcy prediction.

It is possible to see effective use of Artificial Intelligence-based systems in many fields because it easily outperforms traditional solutions or provides solutions for the problems not previously solved. Prediction applications are a widely used mechanism in research because they allow for forecasting of future states. Logical inference mechanisms in the field of Artificial Intelligence allow for faster and more accurate and powerful computation. Machine Learning, which is a sub-field of Artificial Intelligence, has been used as a tool for creating effective solutions for prediction problems.

In this chapter the authors will focus on employing Machine Learning techniques for predicting data for future states of economic using techniques which include Artificial Neural Networks, Adaptive Neuro-Fuzzy Inference System, Dynamic Boltzmann Machine, Support Vector Machine, Hidden Markov Model, Bayesian Learning on Gaussian process model, Autoregressive Integrated Moving Average, Autoregressive Model (Poggi, Muselli, Notton, Cristofari, & Louche, 2003), and K-Nearest Neighbor Algorithm. Findings revealed positive results in terms of predicting economic data.

Natural flood disasters frequently happen in Malaysia especially during monsoon season and Kuala Kangsar, Perak, is one of the cities with the frequent record of natural flood disasters. Previous flood disaster faced by this city showed the failure in notifying the citizen with sufficient time for preparation and evacuation. The authority in charge of the flood disaster in Kuala Kangsar depends on the real-time monitoring from the hydrological sensor located at several stations along the main river. The real-time information from hydrological sensor failed to provide early notification and warning to the public. Although many hydrological sensors are available at the stations, only water level sensors and rainfall sensors are used by authority for flood monitoring. This study developed a flood prediction model using artificial intelligence to predict the incoming flood in Kuala Kangsar area based on artificial neural network (ANN). The flood prediction model is expected to predict the incoming flood disaster by using information from the variety of hydrological sensors. The study finds that the proposed ANN model based on nonlinear autoregressive network with exogenous inputs (NARX) has better performance than other models with the correlation coefficient that is equal to 0.98930. The NARX model of flood prediction developed in this study can be referred to as the future flood prediction model in Kuala Kangsar, Perak.

The purpose of this chapter is to shed light on researchers and practitioners about sentiment analysis in hospitality and tourism. The technical details described throughout the chapter with a case study to provide clarifying insights. The proposed chapter adds significantly to the body of text mining knowledge by combining a technical explanation with a relevant case study. The case study used supervised machine learning to predict overall star ratings based on 20,247 comments related to Royal Caribbean International services for determining the impact of cruise travel experiences on the evaluation company process. The results indicate that travelers evaluate their travel experiences according to the most intense negative or positive feelings they have about the company.

To review three theoretical research programs accounting for the spread of status beliefs and their effects on inequality, and to identify similarities and differences in scope and theoretical principles in the three. We describe suggestions for further research that we hope readers may wish to pursue.

We summarize recent theory and research, identify areas of overlap and dissimilarity, and show how certain research topics could extend understanding of the processes and make connections among the three programs.

The three programs were built on ideas first codified more than five decades ago. Those ideas have been the foundation for empirical research and findings from that have been used to develop the theories, improving the range of situations addressed and the precision of predictions. While the programs here address similar issues, each presumes different initial conditions and behavioral outcomes. With some overlap, the programs also address different situations and propose different mechanisms for the spread of status.

Our review of the programs is necessarily incomplete, because work continues on the programs. The analyses and suggestions about important topics to pursue are ours, and others may identify other topics for theoretical and empirical development.

We hope that our interpretations of these programs make them more accessible to interested scholars who will extend the theoretical and empirical bases of the work. The processes described have implications for the status of immigrant groups, the social position of women, and the value attached to collector’s objects. We hope to foster applications of these theories to understand and alleviate some cases of unmerited inequality.

The processes involved affect mixed-gender interaction in businesses, hiring biases, anti-immigrant exclusion sentiments, influence and bargaining power of individuals, desirability of certain furniture and clothing styles, ability inferences, and other phenomena. We mention instances where these theories can help to understand processes and to develop interventions to produce desirable outcomes.

No readily accessible summary of these programs and no theoretical comparison of them has yet been developed. Formal theories such as these sometimes seem obscure and we hope to show how they apply to important actual situations. Of course, the interpretations and suggestions in this chapter are our own and the scholars whose work we discuss might interpret the work differently.