Data Scientist | Project Manager

Payal A.

Sharma

Data Scientist with 9+ years of experience ensuring data correctness, deploying complex machine learning and statistical model and algorithm for identifying patterns and extracting valuable insights with domain understanding. Demonstrated ability to effectively engage with technical professionals and end users to identify and translate business requirements. Proven ability to manage group of talented professionals to develop valuable solutions that satisfy business objectives of automotive industry.

About

Beyond my core projects, I travel, involve in badminton, Finance and investments, and also contribute to CSR initiatives, firmly believing in connecting with the people, power of knowledge sharing and collaborative development. It's my way of getting engaged with various teams and with the latest industry trends.

One of my significant achievements includes creating and leading a data analysis and Machine Learning algorithm team to determine the advance retail buying for various suppliers. Advanced Retail Buying helps you unlock the full value of your data so you can grow categories significantly while reducing costs. mass-market retailers, grocery chains, office supply stores and many other categories of retailers, consistently helping them reduce the cost of goods sold by 2%–5%, and in some cases more. Identified strategic growth opportunities and develop win-win programs together with suppliers through leveraging advance analytics to uncover shopper insights, understanding their preferences down to the SKU level.

Timeline

2022

Mercedes Benz RD India

May 2022 - Present

2020

2014

2009

Metro Cash & Carry Pvt. Ltd.

Suez India Pvt. Ltd.

Torrent Power India Pvt. Ltd.

June 2020 - April 2022

December 2014 - June 2020

May 2009 - November 2014

Projects

Torrent Power India Pvt. Ltd.

Mercedes Benz RD India

Metro Cash & Carry Pvt. Ltd.

Suez India Pvt. Ltd.

  • Developed a machine learning framework based on symbolic regression for lithium-ion cell lifetime prediction for efficient battery development and thus enable profitable electric vehicles and a sustainable transformation towards zero emission.

  • Enhanced predictive accuracy for lithium-ion cells by 38% over storage time and 13% over energy throughput, with error reductions of up to 77% for other stress factors.

  • Application uses empirical aging modelling from the cell measurement data, Pandas, Numpy for EDA, cleaning and manipulation. Linear regression to forecast battery degradation and aging of the battery 10 years in advance and XGBoost for Classification of cell for various AMG car lineups, Power BI for visualization. Implemented token-based authentication for RESTful APIs, enabling secure communication and data exchange

  • Achieved enhanced and accelerated cell selection, thus saving significant cost and time of the diagnosis team.

  • Torrent Power has been awarded the Distribution Franchisee for Agra Distribution Circle on 26th February, for a period of 20 years. Revenue Cycle Management : Data analysis of consumer readings for HV and LMV-6 customer , finding abnormalities in consumption patterns and addressing technical issues.

  • The planned population and water demand
    • Per capita water consumption rate through the future: 150 lpcd
    • UFW (mainly leakage) % for the water supply systems to be newly constructed: 16%

  • UFW Reduction Project BWSSB decided to implement second stage UFW reduction project in the East, North, and South East areas in Core area of Bengaluru. The original DPR, for the UFW reduction, prepared in 2007 was updated with the new schedule in 2016. It is recommended that details on DMAs shall be further studied to consider the contract packages for distribution improvement. Application uses intensive water supply transmission data to find the gap between supplied and accounted water which in result is water loss.

Role : Team Lead [EDA, ETL, Classification, Modelling and Visualization]

  • Advanced Retail Buying helps you unlock the full value of your data so you can grow categories significantly while reducing costs. mass-market retailers, grocery chains, office supply stores and many other categories of retailers, consistently helping them reduce the cost of goods sold by 2%–5%, and in some cases more.

  • Identified strategic growth opportunities and develop win-win programs together with suppliers through leveraging advance analytics to uncover shopper insights, understanding their preferences down to the SKU level.

  • Application uses supervised machine learning techniques ,XG Boost, Pandas, Numpy for EDA, cleaning and manipulation for classification, PowerBI for visual representation.

Role : Data Scientist - SDE 2 [EDA, ETL, Classification, Modelling and Visualization]

Role : Data Engineer - SDE 1 [EDA, ETL and Visualization]

Role : Data Engineer - SDE 1 [EDA, ETL and Visualization]

Skills

Python

Numpy

Pandas

Scikit-learn

TensorFlow

Matplotlib

Seaborn

SageMaker

Power BI

AWS / Azure

Agile

Jira + Confluence

Testimonials