Results

Found 3 articles

Clear filters

Employees recruitment: A prescriptive analytics approach via machine learning and mathematical programming
PDF
2020 | Decision Support Systems | Citations: 15
Authors: Pessach, Dana; Singer, Gonen; Avrahami, Dan; Chalutz Ben-Gal, Hila; Shmueli, Erez; Ben-Gal, Irad

Abstract: In this paper, we propose a comprehensive analytics framework that can serve as ... Expand

Abstract: In this paper, we propose a comprehensive analytics framework that can serve as a decision support tool for HR recruiters in real-world settings in order to improve hiring and placement decisions. The proposed framework follows two main phases: a local prediction scheme for recruitments' success at the level of a single job placement, and a mathematical model that provides a global recruitment optimization scheme for the organization, taking into account multilevel considerations. In the first phase, a key property of the proposed prediction approach is the interpretability of the machine learning (ML) model, which in this case is obtained by applying the Variable-Order Bayesian Network (VOBN) model to the recruitment data. Specifically, we used a uniquely large dataset that contains recruitment records of hundreds of thousands of employees over a decade and represents a wide range of heterogeneous populations. Our analysis shows that the VOBN model can provide both high accuracy and interpretability insights to HR professionals. Moreover, we show that using the interpretable VOBN can lead to unexpected and sometimes counter-intuitive insights that might otherwise be overlooked by recruiters who rely on conventional methods. We demonstrate that it is feasible to predict the successful placement of a candidate in a specific position at a pre-hire stage and utilize predictions to devise a global optimization model. Our results show that in comparison to actual recruitment decisions, the devised framework is capable of providing a balanced recruitment plan while improving both diversity and recruitment success rates, despite the inherent trade-off between the two. Collapse

Semantic filters: mathematical model dimensionality reduction

Topics: decision support system explainable artificial intelligence missing data smart city IT personell turnover

Methods: computational algorithm machine learning Bayesian network optimization model experiment
Multimode co-clustering for analyzing terrorist networks
PDF
2018 | Information Systems Frontiers | Citations: 0
Authors: Aleroud, Ahmed; Gangopadhyay, Aryya

Abstract: The phenomenon of terrorism is deemed one of the fundamental challenges in natio ... Expand

Abstract: The phenomenon of terrorism is deemed one of the fundamental challenges in national security. Creating defensive technologies to mitigate terrorist attacks requires a simultaneous investigation of contextual relationships among their various dimensions. We proposed and evaluated a graph-based methodology to analyze terrorist networks through co-clustering in a multimode basis. Since there are many heterogeneous relationships in terrorist networks depending on the dimensions used during analysis, we utilized the clustering indicators of the multimode structure discovered in bi- and multimode graphs. Objects and activities that co-occur during terrorist attacks are identified by applying conventional clustering on those indicators. The novelty of our method is in the incremental creation of the multimode structure using its bi-mode counterparts. Our approach is evaluated using these measures: clustering stability and association confidence. The experimental results yields encouraging results in terms of simultaneous clustering of heterogeneous objects in terrorist networks. Collapse

Semantic filters: mathematical model dimensionality reduction

Topics: terrorist incident communication service infrastructure database system social media decision support system

Methods: cluster analysis experiment k-means clustering term frequency–inverse document frequency computational algorithm
Smart Data Selection and Reduction for Electric Vehicle Service Analytics
PDF
2017 | HICSS | Citations: 0
Authors: Schoch, Jennifer; Staudt, Philipp; Setzer, Thomas

Abstract: Battery electric vehicles (BEV) are increasingly used in mobility services such ... Expand

Abstract: Battery electric vehicles (BEV) are increasingly used in mobility services such as car-sharing. A severe problem with BEV is battery degradation, leading to a reduction of the already very limited range of a BEV. Analytic models are required to determine the impact of service usage to provide guidance on how to drive and charge and also to support service tasks such as predictive maintenance. However, while the increasing number of sensor data in automotive applications allows for more ﬁne-grained model parameterization and better predictive outcomes, in practical settings the amount of storage and transmission bandwidth is limited by technical and economical considerations. By means of a simulation-based analysis, dynamic user behavior is simulated based on real-world driving proﬁles parameterized by different driver characteristics and ambient conditions. We ﬁnd that by using a shrinked subset of variables the required storage can be reduced considerably at low costs in terms of only slightly decreased predictive accuracy. Collapse

Semantic filters: mathematical model dimensionality reduction

Topics: user behavior global navigation satellite system Uber decision support

Methods: machine learning simulation lasso regression regression analysis method data transformation

Page 1 of 1

AIS11

Journals

Conferences

Semantic Filter

Found 3 articles

Employees recruitment: A prescriptive analytics approach via machine learning and mathematical programming

Multimode co-clustering for analyzing terrorist networks

Smart Data Selection and Reduction for Electric Vehicle Service Analytics