Bhanu Prakash
Data Scientist
About
Data Scientist with 6+ years of experience in designing and deploying scalable AI/ML solutions using Python, SQL, machine learning, deep learning, and statistical modeling to drive data-driven decision-making across banking and insurance domains. Expertise in predictive analytics, fraud detection, risk modeling, customer analytics, NLP, and Generative AI applications. Skilled in transforming complex structured and unstructured datasets into actionable insights through feature engineering, exploratory data analysis, model optimization, and advanced analytics. Proficient in Scikit-learn, TensorFlow, Keras, PyTorch, PySpark, XGBoost, Apache Spark, and Snowflake, with hands-on experience in building end-to-end ML pipelines and cloud-native AI solutions using AWS SageMaker, GCP Vertex AI, and Azure ML. Experienced in MLOps, CI/CD automation, MLflow, Docker, Kubernetes, RAG pipelines, LangChain, OpenAI APIs, and vector databases for deploying enterprise-scale intelligent automation and real-time analytics solutions.
Skills & Expertise (81)
Work Experience
Data Scientist
Accenture
May 2020 - Present
Working as a Data Scientist with Accenture, Chennai since May 2020 to till date. Developed and deployed end-to-end machine learning models for predictive analytics, classification, clustering, recommendation systems, and forecasting to solve complex business problems. Built scalable ETL/ELT data pipelines using Python, SQL, PySpark, Apache Spark, and Snowflake for processing large-scale structured and unstructured datasets. Performed data cleaning, preprocessing, feature engineering, exploratory data analysis (EDA), and statistical modeling to improve data quality and model accuracy. Designed and implemented NLP and Generative AI solutions using Large Language Models (LLMs), LangChain, OpenAI APIs, Hugging Face Transformers, and prompt engineering techniques. Developed Retrieval-Augmented Generation (RAG) pipelines and semantic search applications using vector databases such as FAISS, Pinecone, and ChromaDB. Created interactive dashboards, reports, and data visualizations using Tableau, Power BI, Dash, Matplotlib, and Seaborn to support business decision-making. Deployed and managed machine learning and AI solutions on AWS, GCP, and Azure cloud platforms using SageMaker, Vertex AI, Azure ML, EC2, S3, and BigQuery services. Implemented MLOps practices including CI/CD pipelines, model versioning, experiment tracking, automated deployment, model monitoring, and drift detection using MLflow, Docker, Kubernetes, GitHub, and Airflow. Integrated REST APIs, cloud storage services, and distributed data platforms to enable scalable, real-time analytics and automated AI workflows. Applied supervised and unsupervised learning techniques including regression, classification, clustering, anomaly detection, and time-series forecasting for business optimization.
Data Scientist
Accenture
Present - Present
PURE Insurance is a specialty insurance organization where the project focused on leveraging data science and machine learning to enhance underwriting efficiency, claims analytics, fraud detection, customer risk profiling, and policy retention strategies. The initiative involved developing scalable machine learning pipelines, performing large-scale analysis on policy, claims, and customer datasets, and deploying AI-driven solutions on cloud platforms to improve risk assessment, pricing optimization, operational efficiency, and data-driven decision-making across high-net-worth insurance products.
Data Scientist
Accenture
Present - Present
Texas Capital Bank is a financial services organization where the project focused on leveraging data science, machine learning, and Generative AI to enhance fraud detection, credit risk assessment, customer analytics, and intelligent banking operations. The initiative involved building scalable ETL pipelines, developing predictive and NLP-based models, and implementing cloud-native AI/ML solutions to analyze large volumes of transactional, customer, and financial data. The project also utilized Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), and vector databases to automate financial document processing, semantic search, and customer support workflows, improving operational efficiency, risk management, regulatory compliance, and data-driven decision-making across banking services.
Education
B.Tech - JNT University
- · Afghanistan
Certifications
No certifications added yet
Interested in this developer?
Profile Score Breakdown
Profile Overview
Skills (81)
Click a skill to find developers with the same skill
