Santhosh Reddy

About Santhosh Reddy

With over 9 years of experience as a Data Scientist, I specialize in developing and…

Experience

1. Senior Data Scientist

   Truist

   Aug 2022 — Present · US

   As a Data Scientist with extensive experience in machine learning and statistical modeling, I specialize in utilizing XGBoost, Python, and PySpark for data analysis and model development. My expertise includes implementing predictive models using AI/ML algorithms such as Decision Trees, NLP, Regression Models, and Text Analytics, with proficiency in managing categorical and continuous variables using XGB classifiers and regressors. I excel in data profiling and feature engineering, employing MLlib in PySpark for data cleaning and feature selection to enhance model accuracy and performance. Additionally, I have developed robust SQL engines and API libraries using C#, XML, and Python, ensuring seamless data flow and integration. My experience extends to working with deep learning frameworks like Caffe and Neon, applying K-Means clustering in Spark/Scala, Python, and R within Hadoop/Hive environments. I have successfully mapped data from source systems to Teradata using utilities like TPump, FEXP, and MLOAD, and extracted data from XML in HDFS utilizing ETL processes for data preparation and analysis. Furthermore, I have provided configuration management and build support for multiple applications, ensuring successful deployments, and implemented public segmentation using unsupervised algorithms like K-Means in PySpark, delivering actionable insights for targeted strategies and decision-making.