Abhishek Shukla

About Abhishek Shukla

Data Scientist with 4+ YoE across Churn modeling, Performance Scoring, Market Mix Modeling, A/B testing, Gen AI, Demand Forecasting, Predictive Maintenance to drive-$ 8M incremental GMS- Reduction of $14 M in working capital- Budget allocation of $150 million- Reduction downtime expenses by $250k- 4% incremental lift in marketing efficiencyDelivered projects across Data Science, Data Engineering & Data Analysis. Experience working on end-to-end ML sys including model development and deployment – distributed data processing in data engineering to build data pipelines (ELT/ ETL) & data story telling with visualization tools: PowerBI & Tableau. Built machine learning model across supervised learning (predictive modeling, predictive analytics) & unsupervised learning (classification, regression, clustering, anomaly detection) to support customer analytics, marketing analytics & operational analytics. Recently worked with LLMs & RAG-based Gen AI.With a masters degree in Artificial Intelligence & Bachelors in Computer Science, I\'m can handle AI/ML uses cases to drive data-driven decision making, strategic decision making, business impact & thrive in agile/ scrum environments, product analytics, data analytics, advanced analytics, translating business problems into data solutions.Utilized- Spark for data preprocessing (data cleaning, data validation, data ingestion, data wrangling, data mining, data lake/ lakehouse architecture, streaming (Kafka), batch processing)- dbt for feature stores, data models, data warehousing, dimensional modeling for query optimization, schema design, data quality & big data analytics- Scikit learning for machine learning & model building (XGBoost, LightGBM, Random Forests, Decision Trees) with feature engineering, feature selection, hyper-parameter tuning, cross validation, interpretability (SHAP)- Tensorflow, Keras, Pytorch for deep learning (LSTM, Autoencoders, Gen AI, RAG, LLMs, LangChain) with MLOps (MLflow, Docker), Airflow & cloud platform tools (Databricks, git, Snowflake)- AWS, GCP, Azure to scale ML systems ensuring (data governance, model governance, model observability, monitoring, schema evolution) with tools like (S3, Athena, glue, SageMaker, Redshift, BigQuery & CI/CD)- Python, SQL for experimentation, causal inference, statistical inference, statistical modeling, incremental liftS-skills:Technical and non-technical stakeholder communication, cross-functional collaborationData Scientist | Data Engineering | Spark • Kafka • Airflow • ETL • Data pipelines • Lakehouse

Experience

1. Data Scientist

   Chewy

   Jun 2023 — Present · US

   Developed and implemented predictive modeling techniques to drive strategic decision-making and optimize customer engagement. Leveraged advanced machine learning and statistical methodologies to enhance business performance across multiple domains. Conducted causal inference and experimentation to measure the effectiveness of business strategies and customer interactions. Designed and deployed customer analytics frameworks, improving segmentation, personalization, and retention strategies. Built and optimized data-driven marketing models, contributing to revenue growth and operational efficiency. Collaborated cross-functionally with marketing, product, and operations teams to translate data insights into business impact. Worked with large-scale datasets in a cloud-based environment, utilizing Python, SQL, and ML frameworks to derive insights.Key Skills & Technologies: Machine Learning & Predictive Modeling Data Science for Business Optimization Experimentation & Causal Inference Customer Analytics & Personalization Cloud-Based Data Processing (AWS, GCP, Azure) Python, SQL, Pandas, NumPy, Scikit-learn

Education

• Northeastern University

  Master's degree, Artificial Intelligence