Heet Patel Email & Phone Number

Dallas, Tx, Us

Marietta, Georgia, United States

Developed a comprehensive chatbot application using the Azure OpenAI Service with GPT-based models, to answer user questions based on stock market news articles. Successfully increased user engagement by 40%, while overcoming challenges related to cost, response latency, and output quality.Integrated data sources and storage by collecting stock market data from Yahoo Finance API, IBKR API, and stock-related blogs, storing it in Azure Data Lake Factory. Leveraged NLP services for data cleaning and engineered new features using Azure Cognitive Services, improving RAG retrieval accuracy by 50%.Designed a distributed data processing pipeline using PySpark and Azure Databricks to enable parallelized training of machine learning models on large-scale stock market news datasets.Streamlined data retrieval workflow by importing processed data into a vector database using Azure Cognitive Search, optimizing retrieval through RAG techniques based on user prompts.Developed a scalable backend system using Flask to efficiently handle API requests from the frontend. Designed a workflow leveraging the LangChain framework to process inputs, retrieve data from a vector database, and integrate the GPT-4o model for generating final outputs.Leveraged GPU acceleration with Azure Machine Learning, reducing model training and inference time by 30% through smart scaling of GPU resources, making high-performance computations feasible for real-time applications.Fine-tuned the GPT-4o model for financial context by training it on domain-specific data, resulting in a 20% improvement in response relevance and accuracy.Deployed using Docker and Azure Kubernetes Service (AKS), using autoscaling for both CPU-bound and GPU-bound services to handle traffic surges cost-effectively, ensuring a consistent user experience.Implemented an interactive frontend with React.js, allowing users to submit news article links and engage with the Azure OpenAI-powered chatbot.

Ahmedabad, Gujarat, India

Conducted Entity Classification on document images using the PyTorch toolbox Mmdetection, optimizing data mapping team productivity, resulting in an additional $650K in revenue and a 70% increase in customer acquisition.Arrange for stakeholders to participate in regular updates and meetings to discuss the status of the project and to voice any issues or modifications.Investigated effectiveness across diverse document types to inform future project enhancements and optimize classification accuracy.Employed GPU acceleration with CUDA to attain an 82% mean average precision in object detection, leveraging advanced algorithms like FasterRCNN, to enhanced accuracy.Administered comprehensive tasks including data annotation, model training, REST API deployment, and seamless frontend integration, ensuring smooth operational workflows and optimal performance.Developed a data analysis Python script to preprocess image data for optimal modeling, including normalization, orientation adjustments, resizing, and pixel manipulation, merged this script seamlessly with a Flask API to ensure efficient data preprocessing and compatibility with downstream modeling tasks.Supported to the development of AI models for various applications, focusing on Python-based backend development.Over the course of the project, manage stakeholders to guarantee good communication and alignment.Explored advanced machine learning (ML) algorithms and techniques, including deep learning and reinforcement learning.Enhanced data entry efficiency by 80% through effective table detection on images using the RetinaNet deep learning model.Make that project goals are in line with corporate objectives and that stakeholder expectations are fulfilled.Develop trusting bonds with all parties involved, such as CEOs, technical teams, and outside partners.Oversee the daily work of AI/ML projects, making sure that deadlines and deliverables are fulfilled

Ahmedabad, Gujarat, India

Supported to the development of AI models for various applications, focusing on Python-based backend development.Explored advanced machine learning (ML) algorithms and techniques, including deep learning and reinforcement learning.Enhanced data entry efficiency by 80% through effective table detection on images using the RetinaNet deep learning model.Achieved 95% accuracy in extracting text from table cells using Pytesseract OCR tool by detecting table grids. Employed computer vision techniques including dilation, Gaussian blurring, and binary thresholding to enhance text visibility in table images.Implemented a data augmentation pipeline using OpenCV and NumPy to generate diverse variations of image data, expanding the training dataset and improving the robustness of deep learning models.Attained a notable 78% F1 score in text classification through comprehensive statistical analysis employing Multinomial Logistic Regression. Implemented a project using python, skit-learn, NumPy, SciPy and UNIX for detecting handwritten digits using artificial neural networks (Natural Language Processing) and convolutional neural networks.Developed a database using JAVA, SQL, and UNIX for managing a library, with one user as a librarian with limited access and the other as a database administrator.Identified risk level and eligibility of new insurance applicants with Machine Learning (ML) algorithms.Predicted the claim severity to understand future loss and ranked importance of features.Used R 3.X, R2.X and Spark 1.4 to implement different machine learning (ML) algorithms including Generalized Linear Model, SVM, Random Forest, Boosting and Neural Network.Evaluated and optimized performance of models, tuned parameters with K-Fold Cross Validation.Provided analytical support to underwriting and pricing by preparing and analyzing data to be used in auctorial calculations.

Masters Of Science, Business Analytics, 3.8

Bachelor'S Degree, Computer Science, 3.9