International Journal of Applied Decision Sciences (6 papers in press)
Preventing crimes ahead of time by predicting crime propensity in released prisoners using Data Mining techniques
by Benjamin David, RAJA S. P, A. Suruliandi
Abstract: Criminologists and psychologists around the world are finding new initiatives to identify criminals and understand crime scenes. This work focuses on predicting the occurrence of crimes for a released prisoner, based on crime propensity prediction, using a supervised machine learning technique. This original research is intended to design and develop a new dataset of 30 attributes that exists nowhere and is exclusively created to define prisoners so as to differentiate them by their propensity to crime using psychological and behavioural factors obtained from jails and assorted sources. The research incorporates an analysis of seven search methods, in tandem with seven subset evaluation techniques, to undertake feature selection, and nine classification algorithms for the classification of prisoners. It is found that the wolf search algorithm, used with the correlation-based feature subset evaluation technique and radial basis function classifier, performs best providing 97.8% precision, 97.5% recall and low error values.
Keywords: Crime Analysis; Prediction; Crime Prediction; Prison Justice; Prisoner Analysis; Data Mining; Wolf Search Algorithm; Classification; RBF Classifier.
Application of artificial neural networks to assess student happiness
by Gokhan Egilmez, Nadiye Özlem Erdil, Omid Mohammadi Arani, Mana Vahid
Abstract: The purpose of this study is to develop an analytical assessment approach to identify the main factors that affect graduate students' happiness level. The two methods, multiple linear regression (MLR) and artificial neural networks (ANN), were employed for analytical modelling. A sample of 118 students at a small non-profit private university constituted the survey pool. Various factors including education, school facilities, health, social activities, and family were taken into consideration as a result of literature review in happiness assessment. A total of 32 inputs and one output variables were identified during survey design phase. The following survey conduction, data collection, cleaning, and preparation; MLR and ANNs were built. ANN models provided better classification performance with over 0.7 R-square and a smaller standard error of estimate compared to MLR. Major policy areas to improve student happiness levels were identified as career services, financial aid, parking and dining services.
Keywords: student happiness; data analytics; neural networks; regression; higher education policy.
Comprehensive evaluation of performance of 21 Chinese industrial parks based on DEA and IDEA model
by Qian Zhang, Bingjiang Zhang
Abstract: In this paper, based on the DEA model and the inverted DEA model, a new comprehensive evaluation indicator is constructed to evaluate the performance of 21 Chinese industrial parks. The standard DEA model is usually used to evaluate the efficiency of decision making units with desirable variables, while the data information of some decision making units also contains undesirable variables. In order to make more full use of the initial data for evaluation, it is considered to introduce an inverted DEA model for evaluating undesirable variables. The indicators of the two models are then combined for comprehensive evaluation. Using the comprehensive evaluation indicator constructed in the paper, 21 Chinese industrial parks were evaluated. The results show that the performance indicator takes into account the psychological characteristics of human beings, which is more realistic, and also improves the distinguishing ability of standard DEA evaluation.
Keywords: comprehensive evaluation; data envelopment analysis; DEA; inverted data envelopment analysis; inverted DEA; prospect theory; PT; industrial park performance.
Measuring the productivity of the bank branches using data envelopment analysis and Malmquist index
by Kaveh Khalili-Damghani, Batool Rahamni, Melfi Alrasheedi
Abstract: Productivity measurement is assumed as one of the main guidelines to assess the effectiveness and efficiency of organisations. Productivity of the bank branches as main players of financial systems should be measured periodically. In this paper, the productivity and its components (i.e., technical efficiency change and technological frontier change) in 42 profit-making branches of a private bank in Tehran province, Iran, are analysed during the period 2014-2016. Inefficient bank branches are determined. The projection of inefficient bank branches toward efficient frontier is also discussed. Productivity and technical efficiency of production elements of branches of a private bank are investigated by Malmquist productivity index (MPI) and an input-oriented data envelopment analysis (DEA) in constant returns to scale (CRS) and variable returns to scale (VRS) conditions. Based on results, scale inefficiency had the greatest impact on technical efficiency in the case study.
Keywords: bank performance; Malmquist productivity index; MPI; data envelopment analysis; DEA; technical efficiency; technological frontier.
A uniqueness-driven similarity measure for automated competitor identification
by Xin Ji, Yi-Lin Tsai, Adam Fleischhacker
Abstract: Uniqueness is an important source of competitive advantage and a salient aspect for firms identifying competitors and market structure. While marketing research often includes uniqueness as an important aspect of product positioning and product strategy, the existing literature has offered little guidance on operationalising this notion for use in the competitor identification process. This paper proposes a probabilistic similarity measure to quantify a competitive landscape where uniqueness is a key driver of competition. The proposed measure, when used with readily available data and combined with existing clustering algorithms, enables automation of the competitor identification process. Empirical experiments are used to validate the proposed measure. These experiments show that marketers can use readily available data, including social media tags and geographical proximity data, to reveal the same insight as is gathered when using the more laborious and time-consuming approach of traditional consumer surveys.
Keywords: uniqueness; similarity; competitor identification; related social tags.
Lights in the shadows: exploring the need for regulation in shadow banking
by Marina Brogi, Valentina Lagasio
Abstract: Since the outbreak of the economic and financial crisis of 2007-2008, the shadow banking system gained attention and caused concerns among standard setters, policy makers, and academics. This research is aimed at analysing the growth of the shadow banking system and assessing whether and how shadow banking entities should be further regulated. Using an instrument-based definition we infer the need for regulation in the shadow banking system by directly investigating the time series of asset backed commercial paper (ABCP) and securitised real estate loans (SREL). By means of several advanced and refined econometric tests, we explore time series data and find a non-stationary trend. This provides support for the need to regulate shadow banking. Further policy implications are discussed in detail.
Keywords: shadow banking system; financial intermediation; asset backed commercial paper; ABCP; securitised real estate loans; SREL; time series analysis.