Educational and Career Outcome Forecasting Through Machine Learning Analytics

Résumé fourni par la source

Understanding the factors that have impacts on salaries are more and more important in data-driven era. Factors such as education, experience, age, gender, and career choices play a key role in determining salaries. This study applies machine learning (ML) methods to explore the impact of these factors, providing insights that can guide employers and help students make informed career decisions. Multiple machine learning models were applied to predict employee salaries based on degree level, age, experience, gender, and career type. The dataset was obtained from a public source, data.world, and is derived from the US Adult Census data. Three ML algorithms were used: support vector machine (SVM), logistic regression (LR), and random forest (RF) classifier to predict whether salaries are above or below 50K. The models were then evaluated and tested using unseen data to assess their performance. The results exposed that LR classifier attained the highest accuracy in comparison to the other classifiers, whereas in terms of precision and F1-score, the RF performed better. In future work, neural network algorithms, including recurrent neural networks (RNNs) with activation functions like sigmoid and softmax, will be applied to classify predicted salaries as either above or below 50K.

Ce résumé expose les affirmations des auteurs. BNTIC ne l’interprète pas comme une validation indépendante des résultats.