Post Job Free

Resume

Sign in

Data Analyst Scientist

Location:
Cranberry Township, PA
Posted:
April 17, 2023

Contact this candidate

Resume:

Baisali Sant

Data Analyst

Pittsburgh, Pennsylvania, 15086 adwloa@r.postjobfree.com 404-***-****

Professional Experience

The Helper Bees

Data Analyst

Jan 2021 – present

•Creating a Fraud Timesheet Analysis model in partnership with the CFO.

•Developing & Analyzing data-driven metrics to improve customer experience.

•Developing captivating KPI dashboards and reports using Tableau Desktop.

•Load and aggregate data from multiple Postgres databases into BigQuery.

•Write SQL queries to generate tables, views, and validate data.

•Collaborating with data warehouse developers to meet business user needs and maintain data integrity

•Designing visualizations with flexible filters and views to highlight patterns in the data

•Developing ETLs for data sources used in financial and production reporting.

•Presenting data analysis that empowered executives to make data-driven decisions.

Lambda School

Teaching Assistant (Data Science) Part Time

Jan 2020 – Dec 2022

•Manage 10 Data Science students and assist debugging code in Python, provide students with feedback on daily code assignments and weekly sprint challenges, ensure 1:1 reviews, enforce success plans for lower performers.

•Tracked student attendance, graded evaluation projects, and completed student progress reports on time, consistently commended by Lambda staff for accurate and time efficient record keeping and student tracking. Alpha Recon

Data Scientist

Jul 2020 – Dec 2020

•Designed Enterprise Systems Architecture for a big data analytics and machine learning project (ESRM).

•Developed python code to perform API calls from 10+ News websites, processed the data and stored it in a Data lake for threat assessment and risk analysis.

•Collaborated with DevOps and Engineering and Analyst team on Azure DevOps to successfully bring scalable ML models and NLP techniques to the deploying phase and continuously reporting valuable indicators to the intel team. University of Pittsburgh

Bioinformatics Internship

Jul 2020 – Dec 2020

•Assist with routine operation of our sequencing bioinformatic analyze pipeline and visualizations

•Monitored sequencing data quality and create quality summaries.

•Performed analysis of experimental data sets and present results to lab team. Citizens Bank

Personal Banker & Teller

Jan 2014 – Sep 2019

•Conducted individual financial analysis to determine appropriate loan and credit options.

•Responded to all customer queries and issues after performing appropriate research.

•Maintained and updated office process reports, customer profiles on a regular basis.

•Assisted with all new account openings and business deposits, count and balance currency, order cash and file documents. These duties require attention to detail, mathematical skills and competence with specialized software.

Projects

Transaction Security Issues: C4ADS

Apr 2020 – May 2020

•Created a predictive model to identify transactions and companies in Russia and Ukraine that are producing precision materials that can be used in the nuclear fuel cycle.

•Analyzed ~65 million rows of Russian import and export trade data ranging from 2016-2018. .

•Tried 3 different models and clustering to find the most effective one.

•Hosted this demo pipeline with AWS resources, where the stakeholder can easily access and run the script. A demo is hosted with Sagemaker, and a robust script is ready to be run in an EC2 instance.

Spotify Songs Suggester (web app)

Jan 2020

•Built back end Flask API that utilizes 130k tracks from the Spotify Audio Features dataset in Kaggle, joined with web scraped music genres.

•Created a recommendation system based on user

preferences utilizing NLP in a KNN model

•Created an API deliverable of music features data visualizations

Bicycle sharing demand predictor

Oct 2019

•Used random forest tree-based model to predict bike sharing demand, casual and registered users both have a different bike rental pattern, random forest regression has a lower mean squared error and higher r-squared score, high correlation features.

Skills

Pandas NumPy SciPy Matplotlib Tableau Apache Spark Hadoop Machine Learning Scikit-Learn TensorFlow Artificial Intelligence Computer Vision Python R SQL ETL Beautiful Soup MongoDB Docker Flask Git Azure Microsoft Visual Studio AWS Excel

Education

Mumbai University

Executive(online) Masters in Data Science, Business Analytics and Big Data in association with IBM

Jan 2020 – May 2021

Lambda School

Data Science and Computer Science

2019 – 2020

Burdwan University

Bachelors in Science(Electronics)

2003



Contact this candidate