About

Thiyagarajan Palaniyappan is a highly experienced Senior Data Scientist with over 19 years of experience in the field. He has worked on a diverse range of problems in data science, including computer vision, natural language processing, time series, virtual assistant, fraud detection, traditional Machine Learning, and Deep Learning. He has end-to-end experience in Data Science, from initial data exploration to training, deployment, and monitoring. Thiyagarajan is a certified professional in Azure, AWS, Kafka, Docker, Data Scientist, Data Mining, Cassandra SparkMLlib, and Machine Learning Specialty. He has advanced knowledge of statistical analysis and data mining techniques, such as regression, classification, semi-supervised learning, forecasting, decision trees, clustering, and A/B testing. He has experience with deploying machine learning apps developed in Python using Flask framework and deploy them using Jenkins and/or Kubernetes and on-premise cloud using Pivotal Cloud Foundry/Concourse/Vault/Apigee. Thiyagarajan has extensive experience using open source and commercial license OCR tools to scanned documents and perform downstream NLP analytics. He is also experienced with geospatial analytics tools like ArcGIS, GeoPandas, Shapely, and using object detection using Keras, Pytorch, YOLO, Mx-Net, and TensorFlow APIs. He has experience using State of the Art Algorithms like RNN, LSTM, BERT, and XLNET for text classification and time series algorithms like FBProphet, SARIMA, SARIMAX, ARIMA, AR-DEEP (GluonTS) for forecasting. Thiyagarajan has worked on Credit Card Fraud detection model using XGBoost and energy forecasting library like PVLib and NREL. He has experience using LiDAR, satellite imagery, and multi-spectral imageries for computer vision. He has performed feature optimization with applied regularization techniques and hyperparameter tuning, model and data drift. He is experienced using Cloud Solutions- AWS, Azure, Google Cloud for training and deployment of models. Thiyagarajan has experience working with data ingestion pipelines, data transformations, and database tables or functions. He is experienced with feature engineering Larger Dataset using PySpark, EMR, Kinesis, Azure Data Factory, Azure Synapse, and Spark ML to process large-scale distributed datasets. He is experienced with No SQL database like Cassandra, MongoDB, GraphDB, Hive, HBase, and Snowflake. He is also experienced using