Search

An organization's success depends on its employees, and an employee's performance decides whether the organization is successful. Employee performance enhances the productivity and output of organizations, i.e., the performance of an employee paves the way for the organization's success. Hence, analyzing employee performance and giving performance ratings to employees is essential for companies nowadays. It is evident that different people have different skill sets and behavior, so data should be gathered from all parts of an employee's life. This paper aims to provide the performance rating of an employee based on various factors. First, we compare various AI-based algorithms, such as random forest, artificial neural network, decision tree, and XGBoost. Then, we propose an ensemble approach, RanKer, combining all the above approaches. The empirical results illustrate that the efficacy of the proposed model compared to traditional models such as random forest, artificial neural network, decision tree, and XGBoost is high in terms of precision, recall, F1-score, and accuracy. [ABSTRACT FROM AUTHOR]

Early effort estimation is important for efficiently planning the use of resources in an Information Technology (IT) project. However, limited research has been conducted on the topic of effort estimation in agile software development using artificial intelligence. This research project contributes to strengthening the use of hybrid models composed of algorithmic models and learning oriented techniques as a project-level effort estimation method in agile frameworks. Effort estimation in agile methods such as Scrum uses a story point approach that measures, using an arithmetic scale, the effort required to complete a release of the system. This project relied on labeled historical data to estimate the completion time measured in days and the total cost of a project set in Pakistani rupees (PKR). using a decision tree, random forest and AdaBoost to improve the accuracy of predictions. Models were trained using 10-fold cross-validation and the relative error was used as a comparison with literature results. The bootstrap aggregation (bagging) ensemble made of the three techniques provides the highest accuracy, and project classification also improves the estimates. [ABSTRACT FROM AUTHOR]