SAYAN GOSWAMI

Tech-savvy innovator with hands-on experience in emerging technologies and passion for continuous improvement. Skilled in identifying opportunities for technological enhancements and implementing effective solutions. Adept at leveraging new tools and methods to solve problems and enhance productivity. Excels in adapting to fast-paced environments and driving technological advancements.

• Full Stack Data Science & AI. 1.5 years. (On going) From Alma batter
• Python Fundamental Form Great Learning 2 months
• Sql for data analysis Internshala 2 month
• Machine Learning From Internshala 1.5 months
• Data analysis with excel Internshala 1.5 months
• Statistics for Data Science from Internshala Internships 2 Month’s
• DITA (Diploma) fom Webel in MS Word, MS EXCEL, MS Power Point. 12th Month’s

1. CHAT BOT USING PYTHON

Developed an interactive chatbot using Python that can understand user queries and provide relevant responses. Utilized natural language processing (NLP) techniques with libraries such as NLTK and spaCy for text processing. Integrated machine learning models to enhance the chatbot’s ability to handle various topics. Deployed the bot using Flask for easy web-based interaction. The chatbot can be further customized to integrate with APIs for dynamic data responses and support multiple platforms.

This project highlights skills in Python, NLP, machine learning, and web development. 

2. Global Tourism Database Developed

Developed a comprehensive global tourism database using Python to store and analyze tourism-related data across multiple countries. Utilized libraries like Pandas and SQLite for efficient data management, enabling seamless querying and analysis of tourism statistics, such as visitor numbers, destinations, and seasonal trends. Implemented data visualization techniques using Matplotlib and Seaborn for insightful reporting. The project enhanced skills in data handling, database management, and Python programming for data analysis.

3. Yulu Bike Sharing Demand Prediction

Developed and implemented an AI/ML-powered demand prediction system for Yulu Bike Sharing, aimed at optimizing fleet management and improving customer experience. By leveraging historical bike usage data, weather patterns, and time-of-day trends, I built predictive models to forecast bike demand at various locations and times. The solution utilized machine learning algorithms such as Random Forest, XGBoost, and Time Series Forecasting to provide accurate, real-time demand predictions.

Key Achievements:

• Improved fleet allocation by accurately predicting bike demand in different city zones.
• Enhanced operational efficiency by reducing wait times and ensuring bike availability during peak periods.
• Integrated weather data, local events, and user behavior to increase model accuracy.
• Developed a scalable deployment pipeline using Python and cloud platforms, ensuring real-time prediction capabilities.