Summary
Overview
Work History
Education
Skills
Timeline
Generic

Andrina Shrestha

Peoria

Summary

Results-driven Data Engineer & Data Scientist with expertise in real-time optimization, predictive modeling, and big data processing. Skilled in Python, SQL, Spark, and ETL pipeline development, with experience in data structures, machine learning, and cloud computing (AWS, GCP, Azure). Adept at building optimization engines, forecasting models, and anomaly detection systems to drive actionable insights from historical and real-time data. Passionate about leveraging data engineering and analytics to enhance decision-making and operational efficiency.

Overview

2
2
years of professional experience

Work History

Data Scientist

Symphony Infotek Inc. (Client: Sabre)
04.2024 - Current


  • Designed and implemented SQL-based ETL pipelines to automate data extraction, transformation, and loading from BigQuery and PostgreSQL, ensuring data integrity and consistency for predictive modeling.
  • Developed an XGBoost-based predictive model to optimize airline seat pricing, leading to a 10% increase in revenue.
  • Integrated reinforcement learning algorithms to dynamically adjust pricing strategies based on real-time booking trends.
  • Built a K-means clustering model to detect suspicious ticket purchases, enhancing fraud detection accuracy by 15%.
  • Implemented statistical hypothesis testing to validate detected anomalies, effectively reducing false positives in anomaly detection systems.
  • Developed LSTM-based time series models to predict airline passenger demand, improving forecast accuracy by 12%.
  • Applied cross-validation and hyperparameter tuning to enhance model robustness and generalization.
  • Conducted descriptive and inferential statistical analysis to uncover key insights from structured and unstructured data.
  • Leveraged advanced feature selection and dimensionality reduction techniques to improve model efficiency and predictive power.
  • Collaborated with cross-functional teams to develop analytical tools for data-driven decision-making and forecasting.

Data Engineer Intern

Symphony Infotek Inc.(Client: United Airlines)
07.2023 - 12.2023
  • Assisted in designing and implementing SQL-based ETL pipelines to streamline data extraction, transformation, and loading from BigQuery and PostgreSQL, ensuring data accuracy and consistency.
  • Supported the development of batch and real-time data processing pipelines using Apache Spark, improving data flow efficiency.
  • Conducted data validation and quality assurance processes to maintain data integrity for predictive analytics.
  • Helped optimize query performance and data models, reducing processing time by 30%.
  • Collaborated with senior engineers to integrate cloud-based data storage solutions with GCP BigQuery and AWS S3.
  • Assisted in building dashboards and reports for data visualization using Tableau and Power BI.

Education

Master of Science - Data Science

University of The Cumberlands
Williamsburg, KY
05-2024

Skills

  • Programming: Python, Scala,
  • Data Engineering: ETL Pipelines (Airflow, Spark, SQL), Data Warehousing, Data Lakes, Cloud Solutions (AWS, Azure)
  • Databases: PostgreSQL, MySQL, SQL Server, BigQuery, NoSQL (MongoDB, Cassandra)
  • Big Data & Distributed Computing: Apache Spark, Hadoop, Databricks, Kafka
  • Machine Learning & AI: Supervised & Unsupervised Learning, Reinforcement Learning, Classification, Regression, Clustering (K-Means), Time Series Forecasting
  • Model Optimization: Hyperparameter Tuning, Cross-Validation, Feature Engineering, Dimensionality Reduction
  • Statistics & Analytics: Descriptive & Inferential Statistics, Hypothesis Testing, Probability Distributions, Anomaly Detection
  • Visualization & Reporting: Tableau, Power BI, Matplotlib, Seaborn
  • Software Development: Git, Agile, Version Control, API Development

Timeline

Data Scientist

Symphony Infotek Inc. (Client: Sabre)
04.2024 - Current

Data Engineer Intern

Symphony Infotek Inc.(Client: United Airlines)
07.2023 - 12.2023

Master of Science - Data Science

University of The Cumberlands
Andrina Shrestha