Rajesh

Senior Staff & Lead Data Scientist

A data-driven data science professional with around 8 years of experience, splendid technical skills and a firm grasp of business needs in various domains, including Pharma, Agriculture, Food Chain, Apparel, Logistics, Supply Chain, and Retail. Capable of performing detailed data and statistical analysis for business requirements. Highly motivated to achieve new things in the field of research in recent times. Also, experienced as a Mentor & Trainer.

SKILLS

• Programming Language:
  1. Python
  2. SAS
  3. R Programming
  4. SQL
  5. VB Scripting
• Analytical: Machine Learning Algorithms (Supervised learning, Unsupervised learning, Clustering), Special Regression techniques, Deep Learning approaches (CNN,RNN,ANN-TensorFlow,keras,PyTorch),Time Series Forecasting, Natural Language Processing, DASH & StreamlitFramework ,Feature/Model Selection(K-Fold Cross validation, GridSearchCV)
• Statistical: Primitive & Sigmoid Neurons, Sampling, Hypothesis testing, Regression Analysis, Correlation analysis, Multivariate Analysis
• Big data Technology: PySpark
• Testing Framework: Pytest
• Cognitive services: Google Cloud Platform – Vertex AI, Compute Engine, Vision ,Cloud Functions, GCS, GKE, BigQuery, API Gateway and Amazon Web Services (AWS) SageMaker, Lambda, EC2,Step functions, Code Pipeline
• Model Deployment: Apache, Docker, Google Kubernetes Engine, CI CD and CT, ML Pipeline(MLOps)
• Data Visualizations tool: Spotfire ,Tableau
• Cloud Computing DB: Snowflake

KEY DATA SCIENCE PROJECTS

• In Agriculture domain, a forecasting models has been built to estimate the sales of fertilizers at depot level with SKU based on historical sales data and various features. This forecasting is done 5 months in advance to avoid overproduction and overstocking in inventory. Developed various type of Time series model and walk through the story of successive algorithms and lead indicators with an accuracy level of 88%. The product has been implemented in India region
• In Apparel industries, Text summarization model (Extractive and abstractive) has been developed. This model generates important summaries of fashion articles, which are valuable in improving business strategies and influencing apparel design. This engine enables the industry to extract key insights and drive innovation in the apparel sector.
• Project for Subject Retention Predictor ML algorithm based on data from the completed studies in the same therapeutic area using Classification techniques.
• Built ship tracking data analysis dashboard in DASH framework and polygon entry model by using Geographical Information System (GIS) information (Satellite data, Vessel data)
• Building AutoML object detection model for Palm/Non-Green Palm trees in GCP platform especially using Vertex AI, Google Could Storage, Vision-AutoML, Google Kubernetes Engine (GKE)
• Recommendation model is built to find the efficient channel for each drug to sell. Here we had various channels to sell such as social media, email, meeting in person, group meet, online meet, commercial ad in television. Based on drug type and other features, we recommend efficient channel to sell.

WORK EXPERIENCE

Senior Staff & Lead Data Scientist (Dec 2022 - Present)

• Responsible for mentoring and guiding the team in Analytics CoE and formed data science community and mentored members from other teams in the organization.
• Played key role in selecting and setting up the GCP and AWS infrastructure for data science project.
• Led the AI team and responsible for setting up the architecture for end-to-end data science projects, I worked as a technical architect in an MLOps project.
• Created compelling visualizations and interactive dashboards to effectively communicate insights and findings to non- technical stakeholders.
• Work closely with cross-functional teams, including data engineers, business stakeholders to understand business requirements and translate them into technical solutions.

Staff Data Scientist (Dec 2021 &ndas