Sandeep Chakraborty

Sandeep Chakraborty is a seasoned data professional with over ten years of experience in data engineering, data science, and data creatives. With a specialization in creating data analytics ecosystems and planning large BI engagements, Sandeep is well-versed in conceptualizing and building solutions, stakeholder management, and project management. He is proficient in using frameworks like Python, R, and Base SAS, among others, and has experience working with MS SQL Server and GCC Big Query. Sandeep is also skilled in using Tableau and AWS QuickSight for visualization and Advance VBA and MS Excel for BI automation. His expertise extends into other areas, including ETL using tools like Alteryx and SSIS.

Sandeep has extensive knowledge of natural language processing techniques and is well-versed in creating AI/machine learning models using deep learning attention-based bidirectional LSTM networks, CNNs, language models like BERT and its derivatives (roBERTa, XLM-roBERTa), KERAS, Pytorch, and scikit-learn. He has experience in creating text classification models using topic modeling (LDA, LSA), NLP, sentiment analysis, semantic dimension reduction, Bi-Directional LSTM models, and collaborative filtering. He is also proficient in using various supervised and unsupervised methodologies, including regression methods, time series, stacking ensembles, K- Nearest Neighbors, support vector machines, decision tree/CART, random forest, and K-Means and Agglomerative Clustering.

Sandeep is a Professional Scrum Master (PSM I Certified – Scored 97.3%) and has worked for top-tier organizations like Bain & Company, The Boston Consulting Group, and The Smart Cube.