I'm a Full-Stack Data Scientist with a proven track record of driving data-driven transformations across industries. With a passion for leveraging data to solve complex problems, I've been a Data Science consultant for Fortune-500 companies and high-growth startups. Here are some of my notable achievements:

• 🚀 Built end-to-end data pipelines for the Augmented Reality emerging technologies division, bridging a 4-year go-to-market gap with their largest competitior.
• 🎓 Mentored 700 trainees in Data Science programming, best practices, and generative AI through comprehensive training programs.
• 💡 Unlocked new revenue streams and implemented churn reduction strategies for a leading Education-Tech conglomerate.
• 🏆 Achieved a 50% increase in click-through rates through emotion-based targeting, recognized by the Wall Street Journal.

My mission is to continue exploring innovative solutions in the Data Science field, utilizing my skills to create lasting business impact.

With 6 years of experience as a full-stack Data Scientist, I specialize in:

• 🔍 Analytical Expertise: Uncovering actionable insights in Marketing Analytics, Customer/Behavioral Analytics, and Product/Web Analytics.
• 🤖 Machine Learning: Industry-focused ML applications, backed by a master’s degree in Statistics. I build models that transform business strategies into data-driven success.
• 💾 Data Engineering: Managing some of the largest data pipelines in the private sector, including multi-dimensional clickstream and transaction data.
• 📊 Business Intelligence: Developing dynamic, self-service dashboards tailored for stakeholders at all levels, prioritizing design thinking and usability.

• Languages: Python, R, SQL
• Libraries & Frameworks: Pandas, NumPy, Scikit-learn, TensorFlow, PyTorch

• Classification: Naive Bayes, Decision Trees, k-Nearest Neighbors, Support Vector Machines, Logistic Regression
• Regression: Ordinary Least Squares (OLS), Bayesian, Penalized/Regularized Regression
• Deep Learning: Multi-layer Perceptron, CNN, RNN, GAN, Autoencoder, LSTM
• Ensemble Methods: Random Forest, Gradient Boosting Trees (GBT), AdaBoost, XGBoost, Voting, Stacking, Meta-Classifier
• Unsupervised Learning: Clustering methods, Principal Component Analysis (PCA), Association Rule Mining
• Experimental Design: Hypothesis Testing, z-test, t-test, ANOVA, chi-square, A/B testing, Randomization methods, Propensity Score Matching, Difference-in-Differences (DiD), Power Analysis, Bonferroni Correction

• Marketing Analytics: Promotion Affinity, Targeted Advertising, Price Optimization
• Customer Analytics: Survival Analysis, Churn Analysis, Customer Segmentation, Channel Attribution
• Product/Web Analytics: Conversion Funnel Analysis, Behavioral Analytics, Cohort Analysis

• Tools & Platforms: Google Cloud Platform (GCP) DataProc, AWS EC2, Vertex AI, Hadoop, Hive, Apache Spark, Airflow
• Storage: Google Cloud Storage, Amazon S3, HDFS
• Automation & Scripting: Automated pipelines, deployment with Airflow and other orchestration tools.

• Visualization Tools: Looker, Tableau, R-shiny
• Data Analysis: BigQuery, Pandas, NumPy
• Charting Libraries: Plot.ly, Matplotlib, GGplot2

• 📧 Email: [email protected]
• 🔗 LinkedIn: linkedin.com/in/ashrithssreddy
• 🐙 GitHub: github.com/ashrithssreddy
• 🌐 Personal Website: ashrithssreddy.github.io
• 🐦 X: @ashrithssreddy
• 📚 Goodreads: Explore My Bookshelf

Feel free to explore my projects and reach out for collaboration or just to say hello!