Sahithi D Email & Phone Number

Alpharetta, Georgia, United States

Plano, Tx

Leveraged advanced complex SQL querying techniques and ETL to extract, collect, aggregate and analyze datafrom multiple sources, complex and large datasets, databases, including telco domain data.• Implemented data pre-processing, data cleaning, data wrangling, data profiling, data mapping, data validation,data manipulation, data analysis techniques, including handling missing data, applying transformations, featurescaling and demonstrated keen attention to detail which resulted in 25% reduction in inconsistencies and errors.• Conducted exploratory data analysis and feature engineering for pattern recognition, for correlating similar datawithin large datasets and to extract valuable insights, using Python, R and libraries like NumPy, Pandas, scikit-learn, for an analytical overview of data.• Managed and executed algorithmic processes critical to digital and financial operations, such as credit riskassessment models, economic models, fraud detection algorithms, and customer segmentation strategies.• Performed statistical analysis of structured and unstructured data using descriptive and inferential quantitativemethods, like Hypothesis testing, A/B testing, ANOVA, Chi-square tests, to gain insights and uncover meaningfulrelationships in the data.• Collaborated with cross-functional teams to develop specifications and implement AIML, machine learningalgorithms like logistic regression, clustering, Naive Bayes, Random Forest, Decision Trees, CNN, Neural Nets.

Addison, Texas, United States

Played a pivotal role in all phases of data lifecycle, Data Mining, Data Collection, Data Cleaning, DataManagement, Model Development, Validation, Visualization and Performed Gap Analysis• Spearheaded the development of PySpark Applications by using python and Implemented Apache PySpark dataprocessing project to handle data from various RDBMS and Streaming sources.• Handled importing of data from various data sources, performed data control checks using PySpark and loadeddata into HDFS (Hadoop Distributed File System).• Led the establishment of CI/CD pipelines, utilizing GitHub for version control and granting our team full ownershipof the environment, ranging from infrastructure provisioning to repository maintenance and access managementfor the development team.• Took charge of Continuous Integration (CI) and Continuous Delivery (CD) process implementation from Dev to=> staging to => Production systems• Skillfully managed and orchestrated containerized applications and models using Kubernetes, ensuring optimalresource allocation and scalability for data science projects.• Demonstrated mastery in deploying Docker containers within Kubernetes clusters, enhancing the efficiency of data-driven applications and analytics

Developed NLP models for Topic Extraction (Unsupervised learning) to predict why customers call the client byusing algorithms like Text Rank, RAKE, LDA, NMF, GLDA, and Sentiment Analysis, using python.• Worked on data cleaning to ensure data quality, consistency, and integrity using Pandas, PyTorch and NumPy.• Models were developed both in R and Python in conjugation because we used open scoring Standards-based,Open-source Middleware for Predictive Analytics Applications. R was used to convert all the models into PMMLformat which was used as an input for open scoring.• Constructed a semantic layer for a proposed data lake by studying existing data sources and leveraging theconcepts of exploratory data analysis and entity relationship diagram using Erwin Data Modeler.• Participated in ad-hoc Teradata SQL queries to pull transactional data from the Teradata warehouse and matchedthem to all digital touchpoints from big data to move it to a data lake.• Expertly leveraged Airflow to automate and orchestrate data processing tasks, enabling focused efforts on high-impact data analysis and modeling.

Bachelor Of Technology - Btech

Master Of Science - Ms, Data Science