Satya Mallipam

MS Data Science candidate with hands-on experience in statistical modeling, machine learning, and healthcare analytics

Talent

KentMember since May 13, 2026

PythonPandasNumPySQLJupyter Notebooksscikit-learnXGBoostGradient BoostingRandom ForestTensorFlowPyTorchH2O AutoMLStatistical modelingExploratory Data Analysis (EDA)Hypothesis testingExperimental designCross-validationEvaluation metricsClassificationFeature engineeringSMOTEClass-imbalance methodologyModel trainingHyperparameter tuningModel servingTableauMatplotlibSeabornAWSDatabricks

Hire this person

Send a job offer directly to this candidate

PythonPandasNumPySQLJupyter Notebooks

About

MS Data Science candidate (Kent State, May 2026, GPA 3.71) with hands-on experience applying statistical modeling, machine learning, and exploratory data analysis to healthcare and population health datasets; experienced building reproducible analytical workflows, Jupyter notebooks, and decision-support pipelines from raw data to stakeholder-facing output. Analyzed 11,000+ clinical records using Python, SQL, and H2O AutoML – applying experimental design, cross-validation, evaluation metrics (F1, AUC-ROC, precision/recall), and class-imbalance methodology to build predictive risk models achieving 87% F1-score; Springer-published researcher. Proficient in Python (scikit-learn, XGBoost, TensorFlow, PyTorch, Pandas, NumPy) and SQL; built end-to-end ML pipelines covering multi-source data consolidation, model training, hyperparameter tuning, evaluation, and serving; familiar with Azure and Databricks for scalable ML experimentation.

Strong analytical thinking, problem-solving, collaboration, and attention to detail; committed to data governance, privacy, and reproducible work. Authorized to work in the U.S. under F-1 OPT.

Experience

Research Intern - LBRCE - Dept. of Information Technology - Mylavaram, India

(2023-06 - 2024-03)

Supervisor: Dr. A.V.N. Reddy, Associate Professor (ML, Deep Learning, Image Processing)

Built a classification pipeline on 11,000+ patient records (170+ clinical features) using Python, SQL, R, and H2O AutoML on AWS; segmented patients into risk cohorts for early premature-birth risk identification, achieving strong AUC-ROC and F1 performance on held-out test data.
Authored structured technical documentation covering model behavior, experiment results, and evaluation metrics (AUC-ROC, F1, precision/recall) to communicate findings to both technical and non-technical audiences – consistent with R&D reporting standards.
Co-authored a peer-reviewed research paper published at FICTA-2024 (London Metropolitan University), indexed in Springer SIST Series – DOI: 10.1007/978-981-96-0143-1_25