Data Scientist
9 Years of Experience
Pune, Maharashtra, India
-
-
Not Available
9 plus years of experience Data Scientist adept at handling technical and functional aspects of DS science projects in the Supply chain domain. Dexterous in devising complex machine learning and statistical modeling algorithms for identifying patterns and extracting valuable insights. Key Skills include team management, leadership, Python, NLP, Machine Learning, R
Egnyte, SaaS/Cloud Product, Information Technology & Services
Aera Technology
PharmaACE
Egnyte, Aera Technology, PharmaACE, Government of Chhatissgarh, vKulp
Job Title : Sr. Data Scientist
Company name : Egnyte
Period : August 2021 - Present
Summary : Time-Series Forecasting:
• Led Neural Prophet & Fb Prophet-based anomaly detection module deployment using FastAPI & Docker
• Engineered Iso-Forest, DBSCAN-based anomaly detection algorithm with silhouette score as the performance metric
• Explored Zero Inflated Poisson distribution forecasting on clustered user groups to improve forecast MAPE
Natural Language Processing:
• Explored Markov chain and SVC based model for memory-efficient file caching for optimized time & cost
• Developed Generative AI based question generation module using Google’s Language Model – PaLM & MedPaLM
• Designed paragraph summarizer & grammar check modules using GPT & PaLM using differing chunking strategies
• Devised LangChain based embedding system & explored convex hull approach to identify anomalous documents
• Fine-tuned GenAI based Llama 2 model using QLoRA technique to develop AEC industry specific jargon detection module
• Developed a GPT 3.5 based helpdesk chatbot & performed prompt engineering to include contextual capabilities
• Designed RAG based multi-document QnA service using Elastic Search, FAISS, Query Expansion & GenAI models like GPT / PaLM
• Created OpenAI Whisper-based service for audio-to-text conversion, improved capabilities to include jargon
• Used Deep Learning based PaLM model to design english to SQL translator using LangChain Pydantic parser
Computer Vision:
• Deployed & developed Tesseract 5-based OCR system after benchmarking against PaddleOCR, EasyOCR, MMOCR
• Architected module exploring pre-processing steps like Binarization, Noise Reduction, etc. to improve OCR
• Developed an active learning-based doc-non doc classification service used as a preliminary step for the OCR
Recommendation System:
• Explored SVD, RBM & Bi-Clustering to identify similar users and recommend features to increase product usage
Job Title : Senior Data Scientist
Company name : Aera Technology
Period : September 2020 - July 2021
Summary : • Developed short term demand sensing, multivariate time series algorithm using Vector Auto Regression for an FMCG major
• Conceptualized raw material requirement prediction algorithm using finished goods data for a France based perfume manufacturing firm
• Used Prophet, Boosting, Random Forest, ARIMA etc. for multivariate time series forecasting for supply chain data
Location : Pune, Maharashtra, India
Job Title : Project Manager - Forecasting
Company name : PharmaACE
Period : October 2019 - September 2020
Summary : • Designing Winter Holt model from scratch via BGFS optimization to be deployed at a top pharma manufacturer in US
• Developing NLP based product to classify entities into header & text reducing man-hours
• Conceptualizing ‘Forecasting Assistance Tool’ to take oral user commands and perform analytical operations
• Structuring forecasting model for drug sales prediction through ML & Deep Learning to be deployed at client side
Location : Pune
Job Title : Chhattisgarh Government - Consultant
Company name : Government of Chhatissgarh
Period : November 2017 - February 2019
Summary : • Helped state Government in deploying tech solution for district level ‘Farmer’s Market’ effecting 1.2 lac farmers
• Conceptualized alternate transportation eco-system increasing household income of 200+ individuals by Rs. 10,000 p.m.
• Conceptualized matrices & developed app for improving services in Government Hospitals
• Devised and monitored uptake of app for monitoring attendance of hospital staff
Job Title : Co-Founder
Company name : vKulp
Period : June 2015 - November 2017
Summary : • Achieved annual projected turnover of more than INR 10 million within 6 months of operations
• Realised gross profitability with the initial investment of INR 1.5 million. leading a team of 15 members
• Raised seed funding for start-up inception and negotiated with multiple venture capitalists for series A funding
• Developed algorithm for ‘Order Forecasting Tool’ aiding firm in predicting future demand
• Conceptualized mechanism for ‘Waste Management Tool’ reducing waste 3% below the industry average
• Devised logic for ‘Salesman Performance System’ and ‘Marketing Budgeting Tool’ for operational efficiency
Title : Algorithmic Trading & Quantitative Analysis Using Python
Period : August 2023 - Present
Summary : UC-3b3816f7-a535-4685-97fc-d6ba7e26f33b, udemy.com, https://www.udemy.com/certificate/UC-3b3816f7-a535-4685-97fc-d6ba7e26f33b/
Issuing Authority : Udemy
Title : FastAPI-The Complete Course 2023
Period : July 2023 - Present
Summary : UC-b4902d28-e36e-4b54-a2be-7765b53e14d7, udemy.com, https://www.udemy.com/certificate/UC-b4902d28-e36e-4b54-a2be-7765b53e14d7/
Issuing Authority : Udemy
Title : Deployment of Machine Learning Models
Period : June 2023 - Present
Summary : UC-53b53a8b-58c1-4be3-967f-78c38e5d12ae, udemy.com, https://www.udemy.com/certificate/UC-53b53a8b-58c1-4be3-967f-78c38e5d12ae/
Issuing Authority : Udemy
Title : Facebook Ads & Facebook Marketing Mastery 2023
Period : May 2023 - Present
Summary : UC-d4b12350-2391-4150-89ea-57fd164fd22b, udemy.com, https://www.udemy.com/certificate/UC-d4b12350-2391-4150-89ea-57fd164fd22b/
Issuing Authority : Coursenvy
Title : Build eCommerce Website with Wordpress and WooCommerce
Period : November 2022 - Present
Summary : UC-c8dcee06-f792-43fe-aa2a-91099209a0f7, udemy.com, https://www.udemy.com/certificate/UC-c8dcee06-f792-43fe-aa2a-91099209a0f7/
Issuing Authority : Udemy
Title : Advanced Computer Vision
Period : April 2022 - Present
Summary : credential.net, https://www.credential.net/97ce3ab2-9cc8-4f91-bf94-5e76bcfdf2a9#gs.wpk6nc
Issuing Authority : OpenCV
Title : Python and Django Full Stack Web Developer Bootcamp
Period : December 2021 - Present
Summary : UC-041f4f24-f597-4e9b-b71e-d4da537d60dd, udemy.com, https://www.udemy.com/certificate/UC-041f4f24-f597-4e9b-b71e-d4da537d60dd/
Issuing Authority : Udemy
Title : Complete Outlier Detection Algorithms
Period : August 2021 - Present
Summary : UC-66c03773-a4eb-4980-8d42-79dc438f4a9b, udemy.com, https://www.udemy.com/certificate/UC-66c03773-a4eb-4980-8d42-79dc438f4a9b/?utm_source=sendgrid.com&utm_medium=email&utm_campaign=email
Issuing Authority : Udemy
Title : Docker and Kubernetes: The Complete Guide
Period : July 2021 - Present
Summary : UC-25e933a4-be65-4e3a-8f2f-9dfb16a76eb4, udemy.com, http://udemy.com/certificate/UC-25e933a4-be65-4e3a-8f2f-9dfb16a76eb4/
Issuing Authority : Udemy
Title : How to create animated videos with power point
Period : July 2021 - Present
Summary : UC-05f5b7ee-54f9-43c6-bd52-f325a5b119d5, udemy.com, http://udemy.com/certificate/UC-05f5b7ee-54f9-43c6-bd52-f325a5b119d5/
Issuing Authority : Udemy
Title : Python OOP - Object Oriented programming for Beginners
Period : July 2021 - Present
Summary : UC-dd649a77-0e1c-4a4e-b48e-f6a769cd50a1, ude.my, http://ude.my/UC-dd649a77-0e1c-4a4e-b48e-f6a769cd50a1
Issuing Authority : Udemy
Title : Tableau 2020 A-Z
Period : July 2021 - Present
Summary : UC-c6d5aad8-2463-4956-b115-cb1350799753, udemy.com, https://www.udemy.com/certificate/UC-c6d5aad8-2463-4956-b115-cb1350799753/?utm_campaign=email&utm_source=sendgrid.com&utm_medium=email
Issuing Authority : Udemy
Title : Linux Mastery
Period : June 2021 - Present
Summary : UC-519838eb-6281-4dfb-8fed-8ec4e4f603e7, ude.my, http://ude.my/UC-519838eb-6281-4dfb-8fed-8ec4e4f603e7
Issuing Authority : Udemy Academy
Title : Github Ultimate: Master Git and Github
Period : May 2021 - Present
Summary : UC-c96cc448-9368-451d-90f8-6a650ebe2195, ude.my, http://ude.my/UC-c96cc448-9368-451d-90f8-6a650ebe2195
Issuing Authority : Udemy
Title : Master SQL for DataScience
Period : March 2021 - Present
Summary : ude.my, http://ude.my/UC-ca44fd70-d61b-40cb-9b5e-a0860e6af409
Issuing Authority : Udemy
Title : Open Water Diver
Period : March 2021 - Present
Summary : 2103EL0031
Issuing Authority : PADI
Title : Divide and Conquer, Sorting and Searching, and Randomized Algorithms
Period : September 2020 - Present
Summary : https://coursera.org/share/c75aaf55600704ed93a4e9a0b4341909
Issuing Authority : Stanford University
Title : Introduction to Big Data
Period : August 2020 - Present
Summary : coursera.org/verify/LHY45Z66YZYB
Issuing Authority : UC San Diego
Title : The Introduction To Quantum Computing
Period : July 2020 - Present
Summary : 2P6ZAV9HCB39, coursera.org, https://www.coursera.org/account/accomplishments/certificate/2P6ZAV9HCB39
Issuing Authority : Saint Petersburg State University
Title : Coursera
Period : June 2020 - Present
Summary : 3YHJVX6SZZCE, coursera.org, https://www.coursera.org/account/accomplishments/certificate/3YHJVX6SZZCE
Issuing Authority : Build a Data Science Web App with Streamlit and Python
Title : Multivariate Anomaly Detection: Safeguarding Organizations from Internal Threats
Publication time : 2023
Title : Neural Machine Translation in Low-Resource Setting: a Case Study in English-Marathi Pair
Publisher : ACL Anthrology
Publication
English (Native Or Bilingual), Hindi
Show More