MS Data Science @ ASU
ML Engineering • Data Science • Distributed Analytics • Ranking Systems • Data Analytics
Tempe, AZ • Seeking Summer 2026 ML/Data Science Internships
Graduate student at ASU specializing in production-style machine learning, with hands-on experience building:
- Learning-to-Rank (LTR) pipelines
- Engagement prediction models
- Fairness & explainability workflows
- Deep learning forecasting systems
- Distributed analytics using Apache Spark
I enjoy turning raw data into reliable, scalable ML systems that deliver measurable impact.
Production-style LTR pipeline with offline training + online scoring.
Tech: LightGBM (LambdaMART), FastAPI, PyTest
Focus: NDCG, MAP, feature generation, registry
End-to-end ML pipeline with fairness auditing.
Tech: Scikit-Learn, Fairlearn
Focus: DPD/EOD metrics, leakage prevention, reproducibility
Model interpretation using SHAP, LIME, permutation importance.
Fairness assessment across sensitive groups with group-wise metrics and ethical evaluation.
Large-scale geospatial processing with PySpark.
Beginner-friendly archive showing my early journey in EDA, ML basics, NLP, and deep learning.
Machine Learning: Scikit-learn, LightGBM, XGBoost, LSTM, ARIMA, Prophet
Ranking & Recsys: LTR, LambdaMART, feature pipelines, evaluation
Fairness & Explainability: SHAP, LIME, Fairlearn, AIF360
Data Engineering: Apache Spark, PySpark, ETL pipelines
Databases: PostgreSQL, SQL, NoSQL (RocksDB)
Tools: FastAPI, Git, PyTest, Linux, MLflow (exposure)
Visualization: Tableau, Matplotlib, Seaborn
Arizona State University
M.S. Data Science (Decision & Computing Analytics)
psjharshni@gmail.com
LinkedIn: https://www.linkedin.com/in/jananya-harshni-74718b261/
GitHub: github.com/JananyaPS
This profile reflects my journey from first principles → production-ready ML systems. Always open to collaborations, internships, and research opportunities.