SUJITH PRAKASH PARSA

Machine Learning (Participated in class Kaggle competitions), Information Management and science, Information Visualization, Knowledge Discovery and Data Mining, Statistical Computing and graphics with R, Statistical Computing.

• IPL Win Prediction Analysis Using Decision Tree: The project focused on predicting IPL winners through Decision Tree analysis, involving data preprocessing and analysis. The Decision Tree approach was employed, producing satisfactory results. The findings were reported using Rmarkdown and shared online via rpubs: https://rpubs.com/Sujith_10/IPLwinprediction-finalreport.

• Analysis of Mass Shootings in the USA: The project delved into analyzing mass shootings in the USA, exploring demographics and mental health history. Responsibilities included data cleaning, analysis, and visualization. The project and its corresponding dashboard are accessible online via the rpubs platform: https://rpubs.com/tumun/982952.

• Crop Recommendation and Yield Prediction System: The Crop Recommendation and Yield Prediction System project focuses on recommending crops to farmers based on factors like soil type and groundwater level. It also predicts crop yield based on the chosen crop. The project involved data collection from diverse sources, data standardization, and the development of a recommendation system that suggests top-k crop options in decreasing order of importance.

• SMS Spam Classification: The SMS Spam Classification project focuses on binary classification of SMS messages into spam or ham. Text classification techniques such as bag of words, TF-IDF, word embedding, and feature engineering were applied. The project culminated in a comparison of machine learning algorithms, including Naive Bayes, Logistic Regression, and Decision Trees, to evaluate their accuracy in the classification task.

● Successfully completed the “SAS 9.4 Programming Fundamentals” certification. This helped me in gaining Fundamental Knowledge of SAS programming.

● Successfully completed “Python for Everybody” and “Python Data Structures” courses on the Coursera platform.