Human migration is based on pull factors that individuals evaluate when it comes to moving to a different territory. Likewise, employee attrition is a phenomenon that represents the tendency to a reduction in employees within an organization. This research paper aims to develop and evaluate machine learning algorithms, namely Decision Tree, Random Forest, and Binary Logistic Regression, to predict employee attrition using the IBM dataset available on Kaggle. The objective is to provide organizations with a proactive approach to employee retention and human resource management by creating accurate predictive models. Employee attrition has significant implications for an organization's reputation, profitability, and overall structure. By accurately predicting employee attrition, organizations can identify the factors contributing to it and implement data-driven human resources management practices. This study contributes to improving decision-making processes, including hiring and firing decisions, and ultimately enhances an organization's capital. The IBM dataset used in this study consists of anonymized employee records and their employment outcomes. It provides a comprehensive HR data representation for analysis and prediction. Three machine learning algorithms, Decision Tree, Random Forest, and Binary Logistic Regression, were utilized in this research. These algorithms were selected for their potential to improve accuracy in predicting employee attrition. The Logistic Regression model yielded the highest accuracy of 87.44% among the tested algorithms. By leveraging this study's findings, organizations can develop predictive models to identify factors contributing to employee attrition. These insights can inform strategic decisions and optimize human resource management practices.

Stock markets and stocks have been around for centuries. For investors, forecasting changes in the price of stocks has long been an aim. Using computer tools for information systems can lead to better and more accurate results. Machine learning uses machines to mimic human thinking and habits. This helps in making predictions and decisions based on data. Today, machine learning is common in areas like face recognition, investment advice, and natural language processing. This study proposes a robust framework for stock trading signal classification within the Indian equity market using a Multivariate Random Forest (MRF) approach. Separate Random Forest classifiers are designed to capture the unique market traits of each company. Bootstrap sampling and random feature selection help the ensemble model to find intricate relationships among various technical variables. This method reduces the variance that comes with individual decision trees. By leveraging the ensemble learning capabilities of Random Forest, the model effectively mitigates the risks of overfitting while managing the high-dimensional feature space typical of financial time series. The Multivariate Random Forest-based stock market model offers a more reliable and practical way to classify stock market signals. The model aids in making smarter, data-driven choices for portfolio management and key market drivers.

Vulnerability is one of the prominent features of rural areas due to their distinctive characteristics, such as remoteness, geographical conditions, and socio-economic dependence on primary sectors. Addressing the vulnerability of rural areas in terms of the rural development paradigm is both urgent and relevant. This study aims to address this issue using the current state-of-the-art machine learning method, using the socio-ecological framework and integrated vulnerability index of villages in Lampung Province in Indonesia. The study attempts to predict and classify villages' vulnerability to be applied for better planning and rural development. Based on random forest classification and decision tree algorithm, the results show that the village governance system represented by rural water management and the level of education of village leaders are suitable prediction variables related to the low vulnerability index. This study can draw lessons learned to improve rural development in developing countries.

Project scheduling in resource-constrained mode is one of the most important issues in the field of project management. The main philosophy of this problem is to use less resources while respecting the resource limit to complete the project in a shorter time although other goals can be considered. When a very large amount of data is generated by the meta-heuristic algorithm and there are many variables involved in solving the problem, no other algorithm or technique is able to analyze the output. For this purpose, learnheuristics have the ability to use combined metaheuristics and machine learning tools with high accuracy and in less time to analyze data. The primary purpose of this research is to combine machine learning and genetic algorithms to reduce the project completion time which can lead to a reduction in the cost of the project. Due to the population-based nature of the problem a large amount of initial population was generated. In order to convert the generated schedules into feasible ones, a repair strategy was used. A data matrix was created to import data into the ML model. After specifying the training and testing settings of the model, the decision tree was used to analyze the data of the problem, then its output was applied to the initial population using the displacement or relocation procedure. This manipulated population is given to Genetic Algorithm (GA) and continues until a certain iteration. j60data on the PSPLIB website was used to evaluate the suggested approach. The findings indicate that the implemented approach has improved by 21.75% compared to the normal GA. This improvement means that a better solution could be achieved in less time with fewer calls.

The Kingdom of Saudi Arabia has witnessed a significant surge in online shopping in recent years, fueled by factors like growing internet penetration, smartphone adoption, and government initiatives supporting e-commerce growth. This rise in online activity has led to a corresponding increase in the utilization of online courier services, playing a crucial role in ensuring timely and efficient delivery of goods In this context, understanding public perception of online courier services becomes crucial for businesses to improve their offerings, address customer concerns, and maintain a competitive edge. Social media platforms have emerged as a valuable source of customer feedback and user-generated content, offering insights into customer experiences and opinions. This paper presents a sentiment analysis on online couriers in Saudi Arabia using natural language processing techniques combined with Decision Tree and Support Vector Machine (SVM) classifiers of machine learning. A dataset on customers’ sentiments was created by a crawling process from X social media. Both classifiers perform well, with Decision Tree classifier performs slightly better on accuracy, i.e. 95.01% compared to 93.60% of the Support Vector Machine. Other metrics support the robustness of the classification.

The purpose of this paper is to examine the extent to which the Intelligent Enterprise Resource Planning (I-ERP) System can be used in company operations. Machine learning is embedded in a decision tree algorithm to demonstrate the viability of intelligent technology in an ERP system and to enhance the quality of operations through an I-ERP system. The study consists of two steps. In the first step, the algorithm uses the decision tree algorithm to demonstrate the application of intelligent technology in an ERP system. In the second step, the proposed model analyzes four quality criteria related to company operations through I-ERP system in order to determine whether or not I-ERP has significant improvement on managers’ decisions. As a result, the use of I-EPR may improve the quality of operations, agile respond to market demand, increase the efficiency and the competitiveness in organizations. An illustration example is provided to demonstrate the application of I-ERP.

Plastic bags are used by many people because they are inexpensive, lightweight, durable, and waterproof. Plastic bags, on the other hand, do not break down and can pollute the environment if not handled properly. Indonesia produces a lot of plastic waste and is one of the top ten countries that has a problem with plastic waste. In this study, we used three months of data of real transactions from a grocery store. This study shows how the decision tree can identify patterns on plastic bag usage at a small grocery store by using demography and products purchase. The attribute weights showed that in the hometown, the total of several products bought were the factors that affected the use of plastic bags.

Control chart pattern (CCP) recognition can act as a problem identification tool in any manufacturing organization. Feature-based rules in the form of decision trees have become quite popular in recent years for CCP recognition. This is because the practitioners can clearly understand how a particular pattern has been identified by the use of relevant shape features. Moreover, since the extracted features represent the main characteristics of the original data in a condensed form, it can also facilitate efficient pattern recognition. The reported feature-based decision trees can recognize eight types of CCPs using extracted values of seven shape features. In this paper, a different set of seven most useful features is presented that can recognize nine main CCPs, including mixture pattern. Based on these features, decision trees are developed using CART (classification and regression tree) and QUEST (quick unbiased efficient statistical tree) algorithms. The relative performance of the CART and QUEST-based decision trees are extensively studied using simulated pattern data. The results show that the CART-based decision trees result in better recognition performance but lesser consistency, whereas, the QUEST-based decision trees give better consistency but lesser recognition performance.