Treffer: Analysis and Development of Smoothie Advisor by using Machine Learning.

The study focuses on the development of "Smoothie Advisor", a personalized smoothie recommendation system designed to cater to individual fitness and nutritional goals. The motivation behind this project is driven by the increasing demand for health-focused solutions that support weight loss, muscle gain, and overall wellness. With more people adopting active lifestyles, personalized nutrition has become a key element in enhancing health outcomes, leading to the need for intelligent systems that offer tailored dietary advice. The project aims to leverage machine learning techniques to create a user-centric solution that not only meets nutritional requirements but also aligns with taste preferences and convenience. The research methodology involved empirical data collection using a Google Form survey distributed among 103 participants. The sample was selected using convenience sampling, targeting individuals between the ages of 20-30. Collected data included user demographics, health goals, dietary preferences, and smoothie consumption habits. For data analysis and model development, feature engineering was performed, followed by training using the XGBoost classifier. Other machine learning techniques like Random Forest and Logistic Regression were also evaluated to compare model performance. The web application was developed using Python's Flask framework, ensuring an interactive and user-friendly experience. The study found that the XGBoost model achieved a high accuracy of 80%, making it the most effective technique for generating personalized smoothie recommendations. Analysis revealed that most participants were comfortable with a variety of fruits and vegetables, and 80% did not report any dietary restrictions, indicating a broad preference range for smoothie ingredients. Based on these findings, it is recommended to integrate real-time health tracking and feedback loops to further personalize the recommendations. Future work could involve expanding the system's features to include integration with wearable devices and fitness tracking apps, creating a comprehensive health management platform that adapts to evolving user needs and lifestyle changes. [ABSTRACT FROM AUTHOR]

Copyright of IEOM India Conference Proceedings is the property of IEOM Society International and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)