Analytics Portfolio

California House Price Analysis, UT Dallas:

Led a team of 8 members to design a Machine Learning Linear regression model using R to analyze the housing trends in the California region by considering various variables like income, number of households, etc. Developed hypothesis and evaluated the performance of the model by testing the concepts of econometrics and compared
the accuracy of the model to find the best fit. Our model was able to achieve an overall accuracy of 85%


Predicting Wages of FIFA Players using Machine Learning, UT Dallas:

Led a team of 5 members to design a Machine Learning regression model using R to predict the wages of football players by considering their skills like age, number of goals scored, agility, etc.Evaluated the performance of each model using the Confusion matrix and compared the accuracy to find the best fit. We were able to achieve an accuracy of 95% with our model.

Predicting Consumer behavior using Machine Learning:

Led a team of 4 members to design 2 Machine Learning classification models- K Nearest Neighbour(KNN) and Logistic regression to predict whether a consumer will purchase an iPhone or not by considering factors like age, salary and Gender.Evaluated the results using a confusion matrix and compared the accuracy to find the best fit. By using this technique, we achieved 94% accuracy

Drowsiness Detection via Machine Learning:

Led a team of 5 members and developed automated software with the help of machine learning which detects the movement of the eyes of the driver of the vehicle and triggers an alarm when the driver of the vehicle feels drowsy. By Implementing this technique, we can save 30% of overall accidents.