Hire Great Data Scientists

Senior Data Scientist & Analytics Leader

Summary

Experienced Data Scientist & Analytics Leader with a strong background in predictive modeling, time series forecasting, multivariate analysis, machine learning, deep learning, NLP, computer vision, big data technologies, DevOps tools, databases, programming languages, and visualization tools. Proficient in mathematical, statistical, economical, and financial modeling techniques. Strong team builder. Holds an MBA in Finance and Quantitative Methods from IIM and a B.Tech. from IIT.

Work Experience

Leading E-Commerce Company (Jan 2020 – Present)

Senior Lead – Data Science and Analytics

Responsibilities: Providing data driven business solutions / actionable insights to various business functions viz. Human Resource, Retail, Finance, Manufacturing, Solar, Telecom, Life Sciences etc.

E-Commerce & Retail:

• Created an AI-driven cloud-based delivery management system, optimizing routes, managing fleets, and automating shipment sorting, benefiting retail and e-commerce businesses.
• Designed an innovative image-based product retrieval system for AJIO, utilizing computer vision techniques. This image search engine enhances the shopping experience by providing tailored product results based on color, shape, and texture.
• Conducted Differential and Predictive Market Basket Analysis for Reliance Retail, uncovering valuable insights on consumer buying patterns and seasonal trends. These findings improved sales, offers, and stock management.
• Currently developing a Virtual Fitting Room, employing advanced technologies like Semantic Generation, Clothes Warping, Content Fusion, Dense Pose network, and computer vision to accurately fit 2D clothing onto 3D body images for online customers.

Blockchain Use case:

• Designed & Developed a Tamper-Proof Document Storage System using Hyperledger Fabric Blockchain network. The project was taken as a POC using Node.js for backend and React.js for frontend and CouchDB as a database.

Design and Development of AI Powered HR Platform:

• Created an all-in-one AI-powered People Analytics Platform, handling data from multiple sources, parsing, storage, and API creation for AI microservices. Streamlined deployment with Docker, quality checks, and CI/CD pipeline for Mobile & Web Apps.

Skill Ontology/ Knowledge Graph:

• Pioneered a group-wide Skill Ontology System using Knowledge Graphs for employee upskilling and project allocation. This system identifies skill gaps, suggests courses, and supports unbiased resource allocation with a pending patent application.
• Developed an extensive candidate metadata database for RIL Group by extracting 18 named entity attributes from resumes, enhancing candidate discoverability through advanced search.
• Empowered Hiring Managers and Recruiters to find suitable candidates for any job description from both historical and recent profiles.

Hiring Platform – Video Interview Analysis System:

• Simplified the Hiring Process by recording and ranking offline video interviews, utilizing deep learning models for transcript generation and Natural Language Processing for scoring based on candidate and reference answers.
• Automated the evaluation of pre-recorded video interviews using Deep Learning & Image Processing, enabling parallel processing and significant time and resource savings.
• Developed a Speech to Text Conversion system tailored for various Indian English accents from videos and audios.

COVID-19 – Containment Zone Tracking & Safe Route Suggestions (Special Purpose Use case):

• Created a system for RIL employees nationwide to check containment zone statuses for safe stay and travel, with managers accessing safety status for their teams.
• Designed a system for recommending secure point-to-point routes while avoiding COVID containment zones.

Leading Telecom Service Provider (Apr 2018 – Jan 2020)

Principal Data Scientist

• Provided Data Science solutions for Wire-less / Wire-line consumer business line of Verizon.
• Provided AI/ML solutions for customer Propensity, Churn, Recommendation and NLP/Text Analytics areas for its various business requirements.
• Built an ML Recommendation engine for Verizon’s Wireline products, enhancing customer experience on digital channels through clustering and classification techniques.
• Developed a production-ready ML model for TV attach pattern identification, resulting in a revenue capacity of over 14M USD. Provided an end-to-end solution for Verizon’s Fiber Optic TV attach business, creating a high-propensity scorecard for targeted marketing campaigns.
• Developed a full-stack Text Analytics system with automated text-engine using PySpark, incorporating text classification models, sentiment analysis, text clustering, and topic modeling.
• Created an AI-powered FAQ Chatbot with intent recognition using Sequence-to-Sequence (Seq2Seq) models and various NLP packages.

Top 5 IT Services Company In The World (Aug 2015 – Apr 2018)

Senior Manager – Data Science

Responsibilities: Responsible for using data science and analytics to address clients’ requirements. Interfaced directly with the clients’ business leaders and ensured end to end delivery of analytical solutions as per the budgets and schedules mutually agreed with the clients.

Client: USAA (Insurance and Financial Services, USA)

• Credit Risk Modeling: Developed PD/LGD/EAD models for various lending assets and employed time series forecasting techniques such as Holt-Winter Seasonal, exponential moving average, ARIMA/ARIMAX/SARIMA, VAR, and Vector Error Correction models for assets and liabilities.
• Property and Casualty Analytics: Validated, monitored, and documented Property and Casualty models, including pricing, claims, and loss models, primarily using Generalized Linear Models (GLM).
• Payment Analytics: Created a Lapse (Churn) model using Decision Trees for US-based customers with Life Insurance policies, offering insights into premium payment delays and proactive strategies to boost revenues.

Client: Microsoft Inc. (Hi-Tech)

• Outliers/Anomaly Detection: Detected outliers in business operations, reducing service time and customer dissatisfaction. Optimized hardware configurations across four Global Regions, increasing system stability and reliability, earning recognition from top management.

Leading Energy Sector Player (July 2005 – Oct 2014)

Deputy Manager – Performance Testing, Performance Monitoring & Analytics

• Provided in-house advanced data analytics support to top management, mentoring and overseeing team members, and managing critical business development projects.
• Developed classification models and an in-house analytics system, contributing to a winning streak in international competitive bids and receiving accolades from the Ministry of Power.
• Created time series models for electricity generation, Plant Load Factor (PLF), and operational availability, aiding in performance analysis and improvement strategies for BHEL products and systems.

Education

• Indian Institute of Management (IIM), MBA (Finance, Quantitative Methods), Lucknow, 2012-2014.
• Indian Institute of Technology (IIT), B.Tech., Kharagpur, 2001-2005.

Other

Analytics Domain

Sales and Marketing Analytics, HR Analytics, Financial Analytics, Business Analytics, Operations Analytics, Strategy Analytics, Geospatial Analytics

Sectorial Domain

Telecom, Retail, Banking, Financial Services, Insurance, Hi-Tech (Microsoft), Manufacturing, Energy, Government.

Artificial General Intelligence /Generative AI

NLP, NLG & NLU using Generative AI models: OpenAI API, Various Large Language Models (LLMs), Generative Adversarial Network (GANs), BERT Variants, TRANSFORMER, Autoencoder, Variational Autoencoder, GPT3, Reinforcement Learnings and Diffusion Models. Currently working on Multimodal (Text , Image , Speech and their combinations) Generative Models

Machine Learning

Predictive Modeling – OLS/GLS/GLM, Linear/Non-Linear Regression techniques, ANOVA & ANCOVA modeling

Time series forecasting – AR/MA/ARIMA/ARIMAX/SARIMAX/VAR/UCM, Seasonal Models, ARCH/GARCH/VARCH/VGARCH models for financial volatility measurement

Multivariate Analysis – Multidimensional Scaling (MDS)/Biplots, Principal Component analysis (PCA) & Independent Component Analysis (ICA), Conjoint, Discriminant, Factor and Cluster analysis.

Machine Learning techniques – Decision Trees, Bagging, Boosting, Random Forest, Support Vector Machines (SVM). Market Basket Analysis, Outliers/Anomaly detection, Optimization Methods: Simplex Method, Assignment algos and others to solve the given business problem.

Deep Learning

MLP, CNN Variants, RNN Variants, LSTM Variants, DL Frameworks – TensorFlow, Keras, Pytorch NLP Text Preprocessing, Text Summarization, Cognitive Conversational Chatbots, Language Translation, Text classification/clustering, Sentiment/Opinion Mining, Topic Modeling (LDA/NMF); Static/Dynamic/Attention based word/Doc embeddings. NLP/NLG/NLU using BERT/GPT#3 based Transfer Learning

Computer Vision

Image pre-processing, Object Detection, Classification, Localization and Instance & Semantic segmentation. CNN Architectures – Segment Anything Model (SAM), VGG16/19, U-Net, Region based CNNs, Mask R-CNN, YOLO V3 to V8, ResNet, Inception V4, OCR/ICR engine, OpenCV, SKimage, Image Magic.

Big Data Technology

Hadoop, Pyspark, SparkCore, SparkSQL, SparkML, GraphX, Hive, Kafka, NetworkX , Graph analytics / Link Analysis

DevOps Tools

RestAPI-Flask , Django and FastAPI based, GitLab, Jenkins, Ansible, Docker, Kubernetes

Databases

MySQL, Elasticsearch, Teradata, Oracle, NoSQL Database – MongoDB, Neo4J, Cassandra

Programming Languages

C, C++, SQL, SAS, R, Python, Scala

Visualization

Tableau, PowerBI & D3.js

Managerial Perspective

Good experience/knowledge of Financial Derivatives- Futures, Forwards, Options and Swaps for financial risk mitigation and management. Expertise in various Mathematical, Statistical, Economical and Financial modeling techniques. Proficient in various aspects of Finance and Strategy. Applied understanding of negotiation skills, financial analysis and business strategies.