Data Science Training in Perungudi

• Python fundamentals, OOP, functions, and advanced programming
• Data analysis using NumPy, Pandas, and Polars
• SQL queries and relational database management
• Data cleaning, transformation, and processing
• Git and GitHub for version control
• Building basic ETL pipelines using Python

Beginner Build an automated Python pipeline extracting API data, cleaning it, and loading to PostgreSQL.

• Basic linear algebra and calculus for data science
• Probability, distributions, and statistical concepts
• Descriptive and inferential statistics
• Hypothesis testing and A/B testing
• Data visualization and exploratory data analysis (EDA)
• Statistical analysis and business data interpretation

Beginner to Intermediate Develop a customer segmentation system using statistical analysis and clustering to identify business opportunities.

• Introduction to machine learning and its applications
• Supervised learning – Regression and Classification
• Unsupervised learning – Clustering and PCA
• Decision Trees, Random Forest, and SVM
• Neural networks and deep learning fundamentals
• Model training, testing, and performance evaluation

Intermediate Develop a customer churn prediction model to identify users likely to stop using services.

• Advanced algorithms using XGBoost, LightGBM, and CatBoost
• Feature engineering and feature selection
• Time-series forecasting and trend analysis
• Recommendation systems
• Handling missing values and imbalanced datasets
• Model interpretation using SHAP and LIME

Intermediate Build a real-time fraud detection system using XGBoost to identify suspicious financial transactions.

• Model deployment using Flask and FastAPI
• Docker fundamentals and containerization
• Experiment tracking using MLflow
• Model versioning and management
• CI/CD pipelines for machine learning
• Model monitoring and performance tracking

Advanced Deploy an ML model via FastAPI and Docker, setting up an automated CI/CD pipeline.

• Introduction to Big Data processing
• Data processing using Apache Spark and PySpark
• Vector database fundamentals
• Working with Pinecone, Chroma, and Milvus
• Text embeddings and semantic search
• Data ingestion and retrieval techniques

Intermediate to Advanced Build a vector-powered semantic search engine to query large PDF corpora using natural language.

• Introduction to Generative AI and LLMs
• Transformer architecture and attention mechanisms
• Prompt engineering techniques
• Working with OpenAI and open-source LLMs
• Model fine-tuning using LoRA and QLoRA
• LLM evaluation and hallucination management

Advanced Fine-tune an open-source LLM using QLoRA to act as an expert domain assistant.

• Introduction to RAG architecture
• Document loading and text chunking
• Embeddings and vector database integration
• Semantic search and information retrieval
• Advanced RAG and GraphRAG fundamentals
• RAG evaluation using RAGAS and DeepEval

Advanced Build a GraphRAG-powered assistant ingesting corporate documents to provide cited, highly accurate answers.

• Introduction to AI agents and agent workflows
• Reasoning, planning, and memory management
• Model Context Protocol (MCP) fundamentals
• Building custom MCP servers
• Tool calling and API integration
• Multi-agent systems and workflow automation

Expert Create an MCP-powered agent to query databases, check CRM, and draft automated follow-ups.

• Computer vision and image processing
• Convolutional Neural Networks (CNNs)
• Natural Language Processing (NLP)
• Vision-Language Models (VLMs)
• Speech recognition using Whisper
• Model optimization using ONNX and TensorRT

Expert Build a multimodal API using VLMs to analyze images, extract audio, and generate descriptions.

• AI security fundamentals and prompt injection
• AI guardrails and output validation
• Data privacy and PII protection
• AI model testing and evaluation
• Bias detection and responsible AI
• AI monitoring and performance assessment

Advanced Build a secure AI research system filtering hallucinations and PII using strict automated guardrails.

• End-to-end data science project development
• Data collection, cleaning, and analysis
• Machine learning model development
• AI application development and deployment
• Resume building and GitHub portfolio preparation
• Technical interviews and career guidance

Expert Deploy a full-stack AI data science application from scratch with ML, GenAI, and scalable backend.