I'm Smit PATEL.

∗ Led the development of a high-accuracy (99.045%) predictive model for company bankruptcy using a comprehensive financial dataset (97 columns, 6820 rows, 10 years) ∗ Implemented advanced data cleaning and feature selection techniques, ensuring robust data quality and meaningful financial insights for stakeholders ∗ Utilized machine learning models to analyze key financial indicators, enhancing decision-making processes for creditors and investors ∗ Conducted extensive data analysis and model validation, significantly improving the reliability and performance of financial risk assessments

∗ Led a 3-member team in creating a predictive model using SPSS Modeler and Python to evaluate candidate retention (0 or 1) utilizing the provided Training Data, a pivotal component of our project’s success ∗ Addressed data quality and model accuracy challenges through thorough data cleaning, normalization, and reclassification, resulting in a 98% accuracy rate on the Test Data set, bolstering the model’s reliability and effectiveness

∗ Engineered an IPR(Intellectual property rights) Filing System in Python with PostgreSQL, enhancing filing accuracy and operational efficiency ∗ Leveraged Docker for containerization, achieving consistent deployment across development and production environments. ∗ Integrated AWS EC2 for hosting and S3 for scalable data storage, optimizing cloud resource utilization ∗ Implemented Jenkins for CI/CD pipelines, automating testing and deployment processes for faster release cycles

∗ Developed an advanced Face Mask Detection system using Python, leveraging CNN, TensorFlow, and Keras, achieving 95 ∗ Integrated CCTV and webcam functionalities for live face capture and mask detection, processing over 1000 frames per second ∗ Conducted data analytics on 10,000+ captured faces to enhance the detection algorithm’s precision ∗ Collaborated with a team of 3 to ensure robust performance and deployment of the detection system in industrial environments

∗ Executed a Text Data Manipulation and Analytics project using Python, implementing the Bag of Words model for text visualization and NLP ∗ Conducted comprehensive text cleaning, including converting text to lowercase and word tokenization, processing over 50,000 text entries. ∗ Utilized word tagging (POS tagging) and analyzed tag information, enhancing the accuracy of text data categorization by 20 ∗ Automated the counting of each word and tag information extraction, significantly improving the efficiency of text data processing workflows

∗ Analyzed 9 years of champagne sales data to forecast future sales trends using advanced statistical techniques ∗ Performed stationarity checks with rolling statistics and the Augmented Dickey-Fuller test, applying differencing to achieve stationarity ∗ Developed and compared ARIMA and SARIMA models, selecting the SARIMA model for optimal forecasting accuracy ∗ Successfully implemented the SARIMA model to predict future sales, enhancing decision-making processes with data-driven insights

∗ Engineered a fully functional ed-tech platform using the MERN stack (MongoDB, ExpressJS, ReactJS, NodeJS) to enable users to create, consume, and rate educational content ∗ Designed and implemented a responsive and interactive front end with ReactJS, enhancing user engagement and learning experience ∗ Developed a robust back end with NodeJS and ExpressJS, providing secure user authentication, course management, and seamless integration with Cloudinary for media handling ∗ Deployed the platform using Vercel for the front end and Render for the back end, ensuring scalability, security, and reliability of the application