Cloud based Student Employment Recommendation Platform using Opposition-based Learning with Skill Optimization Algorithm and Multi-Layer Perceptron

With the help of computer technology, the English teaching has achieved improvements gradually through internet. This research builds a student employment recommendation platform based on Machine Learning (ML) algorithms and attains personalized recommendation through cloud computing. The Opposition-Based Learning with Skill Optimization Algorithm and Multi-Layer Perceptron (OBLSOA-MLP) is proposed in this research for student employment recommendation platform. The OBLSOA helps to reduce the correlation between features thereby improving the feature selection step and creating a model with fewer interpretations. This simplified feature selection contributes positively on computational performance and enhances the quality of the recommendations. This work provides MLP to high relevance to a flexibly developing platform that help students during their job search and enhance their possibilities. The collected data is preprocessed by normalization which normalize the data in the range of 0 and 1. The recall, accuracy, f-measure and precision are estimated for OBLSOA-MLP performance. The MLP obtains 0.953 recall, 0.978 accuracy, 0.947 f -measure and 0.921 precision which is better than existing methods.