H1B_Visa_Prediction_Machine_Learning

● Worked on H1B Dataset where we worked with around 300000 rows of data collected on Kaggle ● Performed data pre-processing on the dataset to remove null values, normalize values to a particular scale and remove outliers by outlier detection, applied and used feature selection to select the best features. ● Removed the imbalance issue in the dataset by using the under-sampling technique. ● Applied KNN, Naïve Bayes, Decision Trees, Neural Networks, and SVM Machine Learning classification algorithms to predict whether a particular application will get approved or not.