M
Madhavi Thatha
About
Detail
Gujarat, India
Résumé
Jobs
verified_user
0% verified
AI EngineerAmeriprise FinancialAug 2025 - Current (1 year 1 month)• Developed and deployed a cutting-edge recommendation system leveraging advanced machine learning and deep learning algo rithms (RNN, CNN, Transformers) in TensorFlow and Keras, resulting in a 35% boost in recommendation accuracy and a 25% enhancement in recommendation relevance. • Utilized Python (Pandas, NumPy, Scikit-learn) to preprocess, engineer, and tune models, optimizing prediction accuracy and performance on over 1TB of data through techniques such as data augmentation and dimensionality reduction. • Architected and managed scalable data warehousing solutions by integrating AWS services (Amazon S3, Redshift, Glue), resulting in a 45% reduction in data retrieval times and a 20% increase in data processing efficiency. • Leverage- ML EngineerLenskart.comJan 2021 - Jul 2023 (2 years 7 months)
- ML EngineerLenskartJan 2021• Implemented Random Forest, Support Vector Machines (SVMs), and Convolutional Neural Networks (CNNs) to achieve 95% accuracy in threat detection and user assistance features. • Collaborated on designing and optimizing scalable applications on AWS, leveraging advanced model optimization techniques and AutoML, resulting in a 40% improvement in processing speed and a 20% increase in prediction accuracy. • Utilized Docker for containerized deployments and established robust CI/CD pipelines with Jenkins and GitHub, leading to a 30% increase in deployment efficiency and a 50% reduction in system downtime. • Developed robust applications using Django, Flask, and REST APIs, implementing microservices architecture and serverless computing with
- ML EngineerInforDec 2020• Designed and implemented a time-series forecasting solution using Python and Facebook Prophet to predict regional sales and demand fluctuations, resulting in a 30% improvement in forecasting accuracy. • Applied deep learning techniques (LSTMs and CNNs) to enhance long-term demand prediction models, particularly in high-volume product categories. • Used NLP methods such as TF-IDF and sentiment analysis to analyze customer feedback and support logs, extracting actionable insights that helped refine product recommendations and sales strategies. • Performed data preprocessing, missing value imputation, and feature engineering using Pandas, NumPy, and scikit learn, streamlining the modeling pipeline and reducing data preparation time by 40
- ML EngineerInforJan 2020 - Dec 2020 (1 year)
Education
verified_user
0% verified
- Master of ScienceCampbellsville UniversityAug 2023 - May 2025 (1 year 10 months)
- GGetting Start With AWS Machine Learning
- AAWS ML Engineer
- HHow Google Does Machine Learning
- DData Science Math Skills
- BBuilding AI Agents
- AAI/ML Algorithms and techniques
Projects (professional or personal)
verified_user
0% verified
- HHousing Price Prediction using Machine LearningOct 2024 - Feb 2025 (5 months)• For this project, I built a housing price prediction model from scratch. I started by collecting and preprocessing the data, handling missing values, and performing feature engineering to ensure relevant features like location, size, and amenities were included. • After processing the data, I implemented various machine learning algorithms, including linear regression, to build the model. Finally, I evaluated the model's performance and fine-tuned it to improve accuracy. This project allowed me to gain hands-on experience with data analysis, feature selection, and predictive modeling. • After running the housing price prediction model, I achieved results with an acceptable level of accuracy. Using metrics such as Mean Absolute Error (M
- HHousing Price Prediction using Machine LearningOct 2024 - Feb 2025 (5 months)• For this project, I built a housing price prediction model from scratch. I started by collecting and preprocessing the data, handling missing values, and performing feature engineering to ensure relevant features like location, size, and amenities were included. • After processing the data, I implemented various machine learning algorithms, including linear regression, to build the model. Finally, I evaluated the model's performance and fine-tuned it to improve accuracy. This project allowed me to gain hands-on experience with data analysis, feature selection, and predictive modeling. • After running the housing price prediction model, I achieved results with an acceptable level of accuracy. Using metrics such as Mean Absolute Error (M
- CCharacterizing and Prediction of Early ReviewersMar 2020 - Sep 2020 (7 months)• For this project, I focused on characterizing and predicting early reviewers on e-commerce platforms like Amazon and Yelp. I explored how early reviews influence product success and consumer decisions. • I used a margin-based embedding model to predict which users are likely to leave early reviews, leveraging a game theoretic approach to understand reviewer behavior. This model analyzes user behavior and predicts which users are likely to post early reviews, based on their interactions and historical data. • By doing this, I helped identify key users who can be targeted for effective product marketing, ultimately enhancing product visibility and success.