Companies always seek ways to make their professional employees stay with them to reduce extra recruiting and training costs. Predicting whether a particular employee may leave or not will help the company to make preventive decisions. Unlike physical systems, human resource problems cannot be described by a scientific-analytical formula. Therefore, machine learning approaches are the best tools for this aim. This paper presents a three-stage (pre-processing, processing, post-processing) framework for attrition prediction. An IBM HR dataset is chosen as the case study. Since there are several features in the dataset, the “max-out” feature selection method is proposed for dimension reduction in the pre-processing stage. This method is implemented for the IBM HR dataset. The coefficient of each feature in the logistic regression model shows the importance of the feature in attrition prediction. The results show improvement in the F1-score performance measure due to the “max-out” feature selection method. Finally, the validity of parameters is checked by training the model for multiple bootstrap datasets. Then, the average and standard deviation of parameters are analyzed to check the confidence value of the model’s parameters and their stability. The small standard deviation of parameters indicates that the model is stable and is more likely to generalize well.

No abstract

Public transport is amongst critical infrastructures in modern cities, especially megacities, home to millions of people. The reliability of these systems is highly crucial for both citizens and service providers. If service providers overlook system reliability, a considerable amount of expenses will be wasted. Several factors such as vehicle failure, accident, lack of budget weather factors, and traffic congestion cause unreliability, among which vehicle failure plays a prominent role. The brake system is the most vulnerable and vital component of a public transportation bus. Brake reliability depends on driver’s expertise, component quality, passenger loading, line situation, etc. Driver’s expertise and components’ quality are the most important factors for brake system reliability. This study aims to implement a hybrid machine learning and optimization model to minimize the total investment and reliability-related costs in a bus rapid transit (BRT) system. A regression analysis method is proposed to capture the main attributes of a joint brake system, including the level of education, training, and drivers’ experience. The failure rate is modeled as a linear function of ETE and the quality of brake system subcomponents using a Lasso regression model. MILP optimization is then provided for optimizing the total expected costs for a bus rapid transit (BRT) system. Furthermore, a practical case is studied to investigate whether this optimization can reduce costs. The results confirm the efficiency of the hybrid optimization approach.