Foram Upala

• Recent AI/ML graduate with a Master's degree in Artificial Intelligence, proficient in Python, R, and SQL for data manipulation and analysis. Hands-on experience includes TensorFlow, PyTorch, and scikit-learn for building machine learning models. Skilled in data preprocessing, feature engineering, and model evaluation techniques, with familiarity in deploying models on AWS and GCP cloud platforms. Possesses strong analytical and problem-solving abilities, effective communication skills, and a collaborative team spirit, eager to contribute to innovative AI projects. ComforRecent AI/ML graduate with a Master's degree in Artificial Intelligence.
  Proficient in Python, R, and SQL for data manipulation and analysis.
  Hands-on experience with TensorFlow, PyTorch, and scikit-learn for building machine learning models.
  Skilled in data preprocessing, feature engineering, and model evaluation techniques.
  Familiarity with deploying models on AWS and GCP cloud platforms.
  Strong analytical and problem-solving abilities.
  Effective communicator and team player, eager to contribute to innovative AI projects.
  Comfortable working in diverse operating systems and environments.table working across diverse operating systems and environments.

Internship Projects

Analysis of U.S. Medical Insurance Costs
Duration: [6/12/2023] - [8/3/2023]

• Conducted comprehensive data analysis on U.S. medical insurance costs to identify key cost drivers and patterns.
• Utilized Python (Pandas, Matplotlib, Seaborn, Scikit-learn) to manipulate data, visualize trends, and build predictive models.
• Developed regression models to predict insurance costs, improving prediction accuracy by 15%.
• Provided data-driven recommendations to senior management, influencing the adoption of new pricing strategies.
• Optimized pricing models, enhancing profitability by 10% and aligning premium calculations with significant cost factors.

Predicting Bitcoin Prices Using LSTM
Duration: [8/7/2023] - [9/31/2023]

• Developed a predictive model for Bitcoin prices using LSTM (Long Short-Term Memory) neural networks.
• Collected and preprocessed historical Bitcoin price data from Yahoo Finance for time-series analysis.
• Utilized Python libraries such as TensorFlow and Keras to implement and train the LSTM model.
• Fine-tuned model parameters, achieving a prediction accuracy of 92% in forecasting Bitcoin price movements.
• Conducted thorough model validation and backtesting to ensure reliability and robustness of predictions.
• Contributed to the development of automated trading strategies based on model predictions, enhancing trading efficiency and potential profitability.

Pathfinding and Obstacle Avoidance using A Algorithm*
Course: Artificial Intelligence

• Implemented A* algorithm for optimal pathfinding in a simulated environment, achieving 95% accuracy in dynamic obstacle avoidance.
• Developed and compared pathfinding algorithms (A*, DFS, BFS), demonstrating superior performance of A*.
• Applied AI theory to practical scenarios, enhancing understanding of algorithmic complexity and efficiency.
• Evaluated algorithm performance, providing insights into applications like autonomous navigation in Tesla cars.

Calories Burnt Prediction

Course: Statistical Learning

• Developed a machine learning model in Python using Seaborn and Scikit-learn to predict calories burnt during physical activities.
• Conducted comprehensive data preprocessing to ensure data quality and relevance for model training.
• Implemented machine learning algorithms such as Linear Regression and Random Forest for accurate prediction of calories burnt based on activity types and user profiles.
• Achieved a prediction accuracy of 85% through rigorous cross-validation techniques, validating model reliability.
• Integrated the predictive model into a fitness application, enabling personalized activity recommendations and enhancing user engagement.
• Enhanced proficiency in statistical learning techniques using Seaborn and Scikit-learn, applying them to health-related data analysis.
• Expanded understanding of machine learning concepts and their practical applications in health and fitness domains.