Sanket Dash Sharma

adlqx1@r.postjobfree.com 657-***-**** https://www.linkedin.com/in/sanketdashsharma EDUCATION

California State University (East Bay) Hayward, CA Aug 2019 – May 2021 Master of Science in Business Analytics & Data Science Ramrao Adik Institute of Technology, University of Mumbai Mumbai, India Aug 2015 – Aug 2019 Bachelor of Engineering in Computer Science

TECHNICAL SKILLS

Programming Languages: Python, R, SQL (MySQL, PostgreSQL, Oracle), NoSQL Data Visualization: Tableau, Power BI, Google Data Studio, Looker, Advanced Excel (Pivot Table, VBA, VLOOKUP) Tools & Platforms: Microsoft Office (Word, PowerPoint), Azure DevOps, Jira, GitHub, Docker, SPSS Cloud Technology: Amazon Web Services, Google Cloud Platform Data Science Tools: Statistics, NumPy, Pandas, Scikit-Learn, SciPy, Keras, TensorFlow, PyTorch, Redshift WORK EXPERIENCE

Data Analyst Intern, Simplex Health Ambler, PA Aug 2020 – Feb 2021

Collaborated with Director of Finance to meet requirements of internal teams, reviewed ETL data pipeline and analytical processes for decision making.

Enhanced and optimized analytical capabilities by strategizing solutions, suggesting implementation of database migration.

Created data source in Google Data Studio to interpret large clinical and customer data sets using PostgreSQL and injected it into business intelligence tools for reporting.

Presented PowerPoint and meaningful insights in the form of interactive dashboards using Google analytics, Tableau, Excel to internal stakeholders to increase sales KPI by 10% each month. Data Scientist Intern, iSmile Technologies Chicago, IL May 2020 – Aug 2020

Led the development of Virtual Assistant chatbot products on AWS for client with an accuracy of 90%.

Worked with diverse and cross functional scrum teams using Agile methodologies, planning each phase through AzureDevOps to achieve desired KPI.

Collaborated with various experts and designed complete technical architecture for a timely delivery of the project.

Used machine learning models to analyze real-time click stream data using AWS services like EC2, S3, Sage Maker, Redshift.

Utilized AWS Lambda to code hook the chatbot with the client website on the basis of analyzed data. Student Assistant at AI Team, Cal State East Bay Hayward, CA May 2020 – Present

Working collaboratively with teams to develop a chatbot for Learning Management System (currently Blackboard).

Applying deep learning as a virtual teaching using TensorFlow, NLTK to process huge data from MongoDB using neural network methodologies and NLP models using python.

Presenting Tableau dashboards to the university faculty to help in improving course specific actions. Research Assistant, Cal State East Bay Hayward, CA Jan 2020 – Feb 2020

Worked on a large clinical dataset, which was extracted using Open API integrations from Federal Drug Association, USA.

Developed different quantitative predictive models to predict adverse effects of drugs on a human body helping companies reduce drug complications.

Data Scientist, Pushstart India Mumbai, Feb 2018 – July2019

Analyzed data patterns and used predictive analytics to target potential stakeholders increasing revenue by 20%.

Developed creative A/B test strategies across direct mail, web and seminar channels for marketing team.

Assisted marketing team with quarterly business reviews and presented marketing performance metrics to achieve positive outcomes.

Facilitated growth of clients by forecasting different parameters and finding loopholes in various areas of their business to come up with a solid roadmap.

PROJECTS

Predictive Analytics using IBM SPSS Modeler for Boston Housing (IBM SPSS Modeler)

Used all relevant nodes to set the type and partition the data to perform predictive analytics on boston housing prices.

Utilized standard model selection method to analyze all predictors’ importance on target variable based on various metrics.

Evaluated models and selected one with an accuracy of 88% to perform relationship analysis between predicted value and actual value. Fake News Posts Prediction on Online Media using Natural Language Processing (NumPy, Pandas, Scikit learn, NLP)

Web scraped various articles and used NLTK library to make sense of large text data set.

Used Passive Aggressive classifier and TfidfVectorizer to build various machine learning models.

Validated and evaluated performance of the model achieving an accuracy of 92% in classifying the news to be true or false. Customer Churn Prediction for a store (NumPy, Pandas, Scikit learn, SciPy, Tableau)

Implemented Churn model using python on a complex customer dataset and came up with association rules for a large store to increase customer retention rate by 40%.

Evaluated various quantitative models using K-fold Cross-Validation and used hyper parameter tuning via grid search to achieve maximum accuracy of 88%.

Analyzed the results and visualized business insights to aid decision making using PowerBI. A/B testing on ecommerce marketing dataset (NumPy, Pandas, Statsmodel, Matplotlib, Seaborn)

Performed A/B testing on marketing dataset to identify whether to have a new website page or not.

Used Logistic regression methodology to find correlations in data set and performed exploratory data analysis.