Machine Learning Data Scientist

ANURAG PATIL

USA 949-***-**** ********@***.*** LinkedIn GitHub Portfolio

PROFESSIONAL SUMMARY

Data Scientist with a Master's degree in Business Analytics & extensive experience in ETL, machine learning, & big data processing. Overall, 11 years of experience, proficient in Python, SQL, & intermediate expertise in R. EXPERIENCE

AbbVie Data Analyst 07/2024 – Present

• Spearheaded the design and implementation of a Bayesian hierarchical model to predict comorbidities in patients as part of AbbVie’s Explore on Demand platform—integrating Real-World Data (RWD) and predictive modeling to drive analytics solutions.

• Collaborated with data engineers and infrastructure teams to manage ETL processes and optimize scalable data workflows using SQL, Apache Spark, Hadoop, Cloudera CML, and cloud services—operationalizing robust data analytics and reporting solutions that enhance model performance and deliver actionable insights.

• Developed a standardized, object-oriented Python framework to transform patient data and conduct comprehensive statistical tests (e.g., Chi-square, z-test), enabling agile, ad-hoc analytics and effective cross-functional reporting.

• Designed and deployed a Python package on GitHub that integrated feature selection and Propensity Score Matching techniques to balance treatment and control groups, ensuring high-quality comparisons and adherence to best practices.

• Implemented advanced statistical models to assess disease prevalence before and after drug administration, generating Real World Evidence (RWE) that informed strategic product decisions and supported continuous process improvements. Tata Technologies Analytics Lead 02/2022 – 07/2023

• Utilized advanced NLP techniques to extract & prioritize the top 10 customer pain points from complaint transcripts, significantly enhancing strategic decision-making & optimizing service delivery processes.

• Conducted in-depth energy analysis on engine coolant temperature data to derive patterns & trends; devised strategic fan operation cycles that extended fan life by 30%, demonstrating proficiency in predictive maintenance & optimization.

• Oversaw the collection & analysis of extensive engine cooling performance data; employed Python to manage & scrutinize large datasets, pinpointing crucial temperature-related performance enhancements. Force Motors Business Analyst, Validation Analytics 12/2019 – 01/2022

• Directed a multidisciplinary team to enhance steering wheel returnability, establishing robust data logging protocols & conducting in-depth analyses of test data at varied speeds, which resulted in a 20% improvement in steering functionality.

• Spearheaded the testing & data analysis of brake & clutch systems on a new commercial vehicle model, successfully reducing clutch pedal effort by 1kg through detailed performance evaluations & optimizations. Tata Technologies Sr. Engineer, Product Development 07/2012 – 11/2019

• Designed an optimized minimum length flow path for the hydraulic steering circuit, resulting in a 5% reduction in circuit length compared to the previous design.

• Analyzed steering oil temperature data, leading to the strategic recommendation to integrate a cooling loop into the steering circuit for noise reduction in the steering pump.

KEY PROJECTS

Recommendation Engine - Harnessing a dataset of 125,000 recipes to train a model that delivers personalized & diverse culinary suggestions, enhancing user engagement & culinary exploration. Driver Drowsiness Detection - Implemented & optimized a deep learning model using multiple convolutional & pooling layers, achieving robust binary classification between alert & drowsy states, significantly reducing the risk of accidents due to fatigue. Document Similarity Checker – Developed & deployed user-based app on streamlit which compares the document similarity Summary Generator – Created & launched user-based app on streamlit which can generate summary using multiple LLM models EDUCATION

University of California, Irvine, Irvine, CA

Master of Science in Business Analytics Beta Gamma Sigma Award Recipient Govt. College of Engineering, MH, India

Bachelor of Engineering

SKILLS

Technical - Python, SQL, R, Machine Learning, NLP, Git, Neural Networks, Big Data Processing, Deep Learning, LLM, Data Visualization Dashboards, Hadoop, Hive, AWS, PySpark, Cloudera Machine Learning CML Python Packages - Keras, PyTorch, Tensorflow, Scikit-learn, NumPy, Pandas, Statsmodels, Scipy.stats, Matplotlib, Plotly, NLTK, Spacy

Contact this candidate