Analysis of Employment Competitiveness of College Students Based on Binary Association Rule Extraction Algorithm

Abstract

 Today, assessing competition among college students in the job search is extremely important. However, various methods available are often inaccurate or inefficient when it comes to determining the level of their readiness for work. Conventional techniques usually depend on simplistic measures or miss out on crucial factors responsible for employability. The challenging characteristics of such competitive employment of college students are the lower levels of perceived stress, financing my education, and crucial professional skills. Hence, in this research, the Internet of Things Based on Binary Association Rule Extraction Algorithm (IoT-BAREA) technologies have improved college students' employment competitiveness. IoT-BAREA addresses this situation using a binary association rule extraction algorithm that helps detect significant patterns and relationships in large amounts of data involving student attributes and employment outcomes. IoT-BAREA positions itself as capable of providing insights into features that highly mediate the employability levels among students. This paper closes this gap and recommends a new IoT-BAREA method to help increase accuracy and efficiency in evaluating student employment competitiveness. Specifically, this study uses rigorous evaluation methods such as precision, recall and interaction ratio to determine how well IoT-BAREA predicts students' employability.