The success of a business depends heavily on the business site. Various criteria affect the selection of the business site; hence decision makers will need to come to a consensus when evaluating the criteria that affect the selection of a business site. Decision making involving multiple criteria is a complex task, hence many Multi Criteria Decision Making (MCDM) methods were developed and Analytic Hierarchy Process (AHP) is a commonly used method. In this study, an AHP model for site selection is validated for four utility payment points in Selangor to determine the ranking of these four utility payment points in terms of their sales.
Studies have shown that certain features from geography, demography, trade area, and environment can play a vital role in retail site selection, largely due to the impact they asserted on retail performance. Although the relevant features could be elicited by domain experts, determining the optimal feature set can be intractable and labor-intensive exercise. The challenges center around (1) how to determine features that are important to a particular retail business and (2) how to estimate retail sales performance given a new location? The challenges become apparent when the features vary across time. In this light, this study proposed a nonintervening approach by employing feature selection algorithms and subsequently sales prediction through similarity-based methods. The results of prediction were validated by domain experts. In this study, data sets from different sources were transformed and aggregated before an analytics data set that is ready for analysis purpose could be obtained. The data sets included data about feature location, population count, property type, education status, and monthly sales from 96 branches of a telecommunication company in Malaysia. The finding suggested that (1) optimal retail performance can only be achieved through fulfillment of specific location features together with the surrounding trade area characteristics and (2) similarity-based method can provide solution to retail sales prediction.
Modeling student engagement in computer-based scientific inquiry learning environments presents two challenges. First, extracting the variables that represent a student's engagement in learning and defining the causal relationships among them can be difficult. Such variables are often implicit due to the unobservable nature of mental model. Second, identifying the evidence from student interaction log to infer a student's engagement level is also a major challenge. Such challenge stemmed mainly because students are granted the freedom to formulate and evaluate hypotheses in computer-based scientific inquiry learning environments, not all interactions can be useful to infer the student's engagement level. As such, the assumption that the frequency of interactions correlates with the level of student engagement can often be misleading. Therefore, this research work attempted to identify the variables of student engagement and to determine the Bayesian Network that can capture the causal relationships between the variables. In this study, two variations of Bayesian Network model were handcrafted with the prior probabilities learned using the interaction logs of 54 students. The predictive accuracy of proposed models were benchmarked against Naive Bayes, Decision Tree, and Support Vector Machine. The empirical findings showed that the Bayesian Network model with convergence arc directions outperformed other models, suggesting it is an optimal model for modeling student engagement in INQPRO.