• Designed and developed Deep Neural Networks (DNNs), Natural Language Processing (NLP), and Machine Learning algorithms, including LSTMs, Transformer-based models, and Autoencoders for large-scale production systems, improving solution performance and real-time anomaly detection.• Developed and deployed real-time machine learning models and anomaly detection systems for streaming services (Disney+, Hulu, ESPN) using Databricks, and Spark Streaming, achieving a 15% improvement in detecting service disruptions.• Applied Isolation Forest, Autoencoders, and seasonality models like VAR, VARMA, and SARIMAX to predict service hosting demands for Disney’s streaming platforms. Analyzing seasonal trends, contributing to a 25% improvement in platform performance.• Leveraged Databricks Asset Bundles (DAB), Delta Lake, and MLflow for tracking, managing, and deploying machine learning pipelines in scalable environments.• Developed and deployed machine learning applications using FastAPI, creating efficient endpoints for model inference. Leveraged Docker containers to streamline the deployment process and implemented CI/CD pipelines using Jenkins and Terraform for continuous integration and delivery. Ensuring scalable and reproducible environments for MLOps workflows.

Built an XGBoost-powered loan default prediction model, achieving a 13% improvement in identifying high-risk borrowers, which led to a portfolio profitability increase.● Led the development of a customer segmentation model that increased customer retention by 15% ● Built large-scale data systems and platforms using Azure HDInsight and ● Azure Databricks, resulting in a 40% increase in data accessibility and availability and a 15% reduction in infrastructure costs ● Implementing a personalized recommendation system that improved customer engagement by 25%. Developed and deployed predictive models and machine learning algorithms using Azure Machine Learning and TensorFlow, resulting in a 20% improvement in product performance and customer experience and a 25% increase in conversion rates ● Analyzed and interpreted large datasets with over 100 million rows and 50 variables to provide actionable insights for senior management ● Improved fraud detection accuracy by 20%, resulting in savings of over $10 million annually ● Collaborated with cross-functional teams of up to 20 members to develop and deploy data products, resulting in a 50% reduction in time-to-market

● Conducted analysis on assessing customer consuming behaviors and discover the value of customers with RMF analysis; applied customer segmentation with clustering algorithms such as K-Means clustering and Hierarchical Clustering.● Built regression models include: Lasso, Ridge, SVR, XGboost to predict Customer Lifetime Value.● Developed and implemented predictive models using machine learning algorithms such as linear regression, classification, multivariate regression, Naive Bayes, Random Forests, K-means clustering, KNN, PCA, and regularization for data analysis.● Performed univariate and multivariate analysis on the data to identify any underlying pattern in the data and associations between the variables.● Evaluate models using Cross-Validation, Log loss function, ROC curves and used AUC for feature selection and elastic technologies like Elastic Search, Kibana etc.● Built and tested different Ensemble Models such as Bootstrap aggregating, Bagged Decision Trees and Random Forest, Gradient boosting, XGBoost, and AdaBoost to improve accuracy.

● Developed personalized recommendations for customers based on their usage patterns, resulting in a 7% increase in customer retention rates.● Utilized time series analysis to identify trends and patterns in customer behavior data and provided recommendations to the product team to improve the user experience, resulting in a 15% increase in user engagement.● Implemented cutting-edge machine learning models to predict demand fluctuations and streamline inventory levels, leading to a lean and agile supply chain system capable of adapting to dynamic market conditions.● Designed, built, and developed a set of Python modeling APIs for customer analytics, which integrate multiple machine learning techniques for various user behavior prediction and support multiple marketing segmentation program. ● Conducted exploratory data analysis and feature engineering on large-scale text data, leveraging statistical and machine learning techniques to extract relevant features and improve model performance.

● Utilized time series analysis to identify trends and patterns in customer behavior data and provided recommendations to the product team to improve the user experience, resulting in a 15% increase in user engagement ● Analyzed large data sets to develop multiple custom models and algorithms to drive innovative business solutions.● Performed Data profiling, preliminary data analysis and handle anomalies such as missing, duplicates, outliers, and imputed irrelevant data.● Remove outliers using Proximity Distance and Density-based techniques.● Involved in Analysis, Design and Implementation/translation of Business User requirements.● Experienced in using supervised, unsupervised and regression techniques in building models.● Performed Market Basket Analysis to identify the groups of assets moving together and recommended the client their risks.● Experience in determine trends and significant data relationships using advanced Statistical Methods.● Implemented techniques like forward selection, backward elimination and step wise approach for selection of most significant independent variables.● Performed Feature selection and Feature extraction dimensionality reduction methods to figure out significant variables.

● Involved in defining the source to target data mappings, business rules, and data definitions.● Involved in defining the business/transformation rules applied for sales and service data. ● Worked with project team representatives to ensure that logical and physical ER/Studio data models were developed in line with corporate standards and guidelines. ● Responsible for defining the key identifiers for each mapping/interface. ● Used Python, R, and SQL to create Statistical algorithms involving Multivariate Regression, Linear Regression, Logistic Regression, PCA, Random Forest models, Decision trees, and Support Vector Machine for estimating the risks of welfare dependency