SAMARTH HADAWALE
Boston, Massachusetts 857-***-**** ********.********@*****.***
https://samarthhadawale.github.io/ www.linkedin.com/in/samarthhadawale
EDUCATION
Northeastern University, Boston, MA Expected May 21
Master of Science in Information Systems (GPA: 3.76/4.00)
Courses - DBMS and DB Design, Data Science Engineering, Designing Advanced Data Architectures for BI
Savitribai Phule Pune University, Pune, India Jul 14 – Jul 18
Bachelors of Engineering in Computer Engineering
TECHNICAL SKILLS
Business Intelligence Tools Tableau, MS Power BI, Qlik Sense, Einstein Analytics
Database Management MySQL, Oracle, NoSQL, MSSQL Server
Programming Languages Python, SQL, R, Java
ML frameworks NumPy, Pandas, Scikit-learn, Matplotlib, Plotly, TensorFlow, Conx, Keras
Data Wrangling & Modeling tools Tableau Prep, Trifacta, XSV, Toad Data Modeler, Visual Studio
ACADEMIC PROJECTS
Northeastern University, Boston, MA.
Book Store Marketing and Analytics (Python, R, Flask, Tableau, AWS S3, EC2) Jul 20 - Aug 20
Performed & analyzed Customer Segmentation using RFM modeling, CLV, Cohort Analysis & Sales forecasting.
Developed ‘Books Recommendation System’ for customers to get similar books based on their choices & popularity
Implemented ‘Predictive Analysis System’ for suggesting similar books on the basis of confidence score using R
Explored the dataset staged in AWS S3 & Visualized it for getting valuable insights using Tableau
Integrated all above systems into the Web Application using Flask, HTML, CSS, Bootstrap & deployed it on AWS EC2
Customer behavior analysis using Data Pipeline (XSV, Pandas, Trifacta, Snowflake, Einstein Analytics) May 20 – Jun 20
Joined & explored datasets having 34M+ records using XSV, Pandas
Sampled and performed some key operations on the dataset using Trifacta Data Wrangler
Staged that data into Snowflake data warehouse and forwarded it through live connection to Einstein Analytics
Visualized the data & predicted customer behavior through some exciting dashboards using Einstein Analytics
Health Effects of Increasing Toxic Dumping & Poor AQI (Python, ANN using Conx & Keras) Jan 20 – May 20
Cleaned and integrated AQI, TRI, Cancer and Life expectancy data for 65 US counties from publicly available data sources
Performed EDA on a merged dataset to find correlation between AQI, TRI parameters and cancer rates
Employed Random Forest Regression and PCA to determine most significant features influencing cancer rates
Predicted future cancer rate with an accuracy of 85% using Multi Output Regressor and CNN for model training
United States Health Insurance Program (Talend, Tableau, MS Power BI, AWS). Jan 20 – May 20
Integrated 2M+ records of data from multiple sources to devise a multi-dimensional data warehouse using Talend
Designed ETL workflows using Talend to integrate data into facts and dimension tables of Insurance Data Warehouse
Built 20+ dashboards to analyze main KPI’s using Tableau and Power BI
Used Amazon Web Services (AWS) Redshift to store the warehouse and using AWS Athena to query the warehouse
Stock Market Prediction and Risk Analysis (Python, Machine Learning Algorithms) Jan 20 – Feb 20
Developed a Random Forest Model which predicts the adjusted closing price of 3 industries stock with 80% accuracy
Analyzed the comparative rise of companies using Time Series Analysis & visual EDA using Seaborn, Cufflinks & Plotly
Evaluated the risk to return ratio for each stock to establish safe investment policies with maximum returns
PROFESSIONAL EXPERIENCE
Opulent, Pune India Aug 17 – Jan 18
Data Engineer Intern
Worked on data cleaning & data profiling on the various datasets of clients having around 650 tables and 7M+ rows
Reduced loading time of data by approx.70% by streamlining & capturing historical records by designing Type-2 SCD jobs
Performed ETL workflows by staging that dataset into Talend open studio and further pushed that dataset into Oracle DB
Visualized critical KPI’s in Power BI to analyze the market with respect to prospective and existing clients
RESEARCH WORK
Tsunami alert and Detection system using IoT: A survey (IEEE) Jan 17 – Mar 17
This survey includes methods which helps us to ensure our security before tsunami arrives using some observations.