Python, R, PERL, C, Java, HTML, CSS, SQL, Apache Hadoop, Git, Agile Development,
Tableau, Hypothesis Testing,Data Wrangling, Data Visualization, Cluster Analysis,
Regression Analysis, Ensemble Methods, Communication, TimeManagement.
• Creating a statistics tool to provide engineers with meaningful insights into the
wafer data.
• Working with various volumes of data from multiple sources (frontend wafer test data and
backend packaged test data) and performing data analysis to identify solutions for
engineering problems.
• Developing a tool to enable test/product development engineers to group die level data and
figure out how the bins are yielding in the back-end test flows.
• Set up pipelines to process user data to readable format.
• Performed cleaning and data manipulation to get rid of the outliers.
• Built and tested models (K-Means, DB-Scan, A = CR [Row space clustering], Random Forest)
to find correlations between participants in an event.
• Performed dimensionality reduction (PCA reduction) to reduce the size of data while
keeping the essential features.
• Creating custom applications for automation and reporting purposes.
• Follow agile life cycle to develop applications.
• Building dashboards and visualizations to help make better budget decisions.
• Analyze traffic data to find hotspots and anomalies
• Analyze the properties of different materials to find a suitable combination for Bulk
Metallic Glass.
• Research factors affecting the formation of BMG and perform feature engineering to
increase efficiency of our ML model.
• Classifying Trades as a buy or a sell.
• Extracting data from different stock markets and parse them.
• Filtering out features and applying ML models to the dataset. At present, used
Random Forest Classifier at an accuracy of 75% - 86% based on different
stock markets.
• Collecting tweets from Twitter using the twitter api and raspberry pi for 1-3 days.
• Performing sentiment analysis for certain keywords.
• Graphing the positive and negative sentiment in realtime.
• Scraping the Ada County website for housing data.
• Performing data cleaning and manipulation to parse the data into desired format.
• Applying dimensionality reduction techniques and performing feature selection.
• Trying out different ML models and tune hyperparamters for efficient performance.
• The goal of the task is to advance data-driven parsing into graph-structured
representations of sentence meaning.
• Creating a pipeline to parse the model’s output to a compatible form for evaluation.
• Model in progress and currently has a f1 score of 0.72. Tuning hyperparameters to get
better results.
• Analyzing credit card transaction data obtained from Kaggle for any anomalies.
• Build a K-Means Clustering model to segregate transactions into groups.
• Used Random Forest Classifier to achieve a roc_auc_score of 0.918
• President, Boise State Computer Science Club
• Founding Member, BoiseHacks Club
• Guest Speaker Manager, AI Club
• Relevant Coursework : Data Structures, Algorithms, Calculus 3, Probability and Statistics,
Database Systems
• GEM Scholarship (Non-Resident Scholarship for High Achieving Students)
• Dean’s High Honors List: 4 semesters