Projects
Professional Projects
▪ Scraped data using frameworks like Scrapy, BeautifulSoup, cleaned it and brought it to a structured and usable format using Pandas on a scale.
▪ Created and maintain data processes to add new data points for companies and QA them fast and effectively.
▪ Created and maintain a process to add the latest M&A and funding deals on to the database in a timely and effective manner.
▪ Created new features, dashboards for the platform and worked on creating SQL queries to support data on the dashboard.
Academic Projects
▪ Identifying underlying reasons and Predicting Hate Crime. Collected data from various sources like FBI, US DOJ, Census data to identify reasons for hate crime in the United States of America and predict it.
▪ Text Mining of Donald Trump's linguistic style using Quanteda, TM, NLP in R. Analyzed his speeches to understand his linguistic style and how he connects so effectively with people.
▪ Predicted new store locations for Lowe's and Home Depot Analyzed data for Lowe's and Home Depot and their store opening strategies. Based on data, predicted the location of new stores and validated that data.
▪ Time Series Analysis in R. Proved inverse relationship between Gold and Oil prices using time series. Predicted Oil and Gold prices using the HoltWinter function.
▪ Increase deposits subscription of the bank using Decision trees in R. Analyzed dataset of a Portuguese banking institution to define a strategy to increase deposits subscription using R-part and Rpart.plot packages in R.
▪ Prediction Analysis and visualization of data set using ggplot in R. Analyzed soup company to determine their market share in winter months and non-winter months and predicted sales based on regression model so they can improve their inventory management.
▪ Linear Regression Models - Created numerous linear regression models to establish the relationship between variables and to predict future based upon regression models.
▪ Impact Investing Index - Created an impact investing index based upon scoring scale where we could rate any company for prospective investment based upon the impact on social parameters and financial parameters using R & Excel.
▪ Analyzing and Visualization of the dataset - Data analysis and visualization of data set for U.S. terrorism cases since 2001 to validate the statement that terrorism is an increasing threat in the USA using Tableau.
▪ Descriptive statistics & data visualization of a dataset of the bank, for people receiving loan vs not.
• Analyzing correlation, summarizing and visualization of people receiving loan vs people not receiving the loan and how could banks reduce the risk of bad loans based upon data using R and Tableau.
▪ Data Security policies at J.P. Morgan Chase & Co. This paper focuses on information security and data security at J.P. Morgan Chase & Co. and what are the main security features that they utilize to keep their data secure.
▪ Descriptive analytics, predictive analytics and data visualization of Citibike data using R and Tableau.
• Data Exploration, summary statistics and data visualization using R & Tableau. Developed a predictive model using linear regression to forecast revenue based on variables such as age, gender, income group