AI-Driven Software Framework for Intelligent Optimization of Sugar Reduction Strategies in Confectionery Using Polyols and High-Intensity Sweeteners
Abstract
Growing consumer awareness regarding health and nutrition has increased the demand for reduced-sugar confectionery products.
However, sugar performs multiple functional roles in confectionery systems, including sweetness, bulking, texture formation,
crystallization control, and shelf stability, making its reduction a complex formulation challenge. This study proposes an AI-driven
software framework designed to intelligently optimize sugar reduction strategies in confectionery formulations using polyols and high-intensity sweeteners. The developed framework integrates machine learning algorithms, ingredient property databases, and predictive
modeling techniques to support researchers and product developers in designing optimized reduced-sugar formulations. The software architecture consists of modules for ingredient selection, sweetness equivalence prediction, physicochemical property estimation, and multi-objective optimization. Polyols such as sorbitol, xylitol, and maltitol are incorporated to provide bulking effects and desirablemouthfeel, while high-intensity sweeteners including steviol glycosides and sucralose are used to achieve the required sweetness intensity. A structured dataset comprising formulation ratios, sweetness intensity, water activity, texture parameters, and sensory evaluation scores is used to train supervised learning models for prediction and optimization. The framework applies multi-objective optimization algorithms to balance key formulation constraints including sweetness profile, caloric reduction, crystallization behavior, and storage stability. The proposed AI-enabled approach demonstrates significant potential in improving formulation efficiency and guiding intelligent sugar substitution strategies. This study highlights the interdisciplinary integration of software engineering, machine learning, and food product development for designing healthier next-generation confectionery products.
Keywords:
rtificial Intelligence, Sugar Reduction, Confectionery Optimization, Polyols, High-Intensity Sweeteners, Predictive Food FormulationPublished
Issue
Section
License
Copyright (c) 2026 International Journal on Emerging Research Areas

This work is licensed under a Creative Commons Attribution 4.0 International License.
All published work in this journal is licensed under the Creative Commons Attribution 4.0 International License (CC BY 4.0). This license permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
How to Cite
Similar Articles
- Honey Thomas, Linna Benny, Saya Nezrin, Navya Neethi S, Niya Joseph, Smart Communication Software for the Hearing Impaired Using Artificial Intelligence , International Journal on Emerging Research Areas: Vol. 4 No. 2 (2024): IJERA
- Amrutha Priya C B, Nitha C Velayudhan, Arjun K S, Aleena Francis, Divya P S, AI Enabled Robot for Data Collection in Unreachable and Extreme Environment , International Journal on Emerging Research Areas: Vol. 4 No. 1 (2024): IJERA
- Honey Joseph, Aaron Samuel Mathew, Adhil P, Alan Siby, Alwyn Joseph, Potato Leaf Disease Detection Using VIT , International Journal on Emerging Research Areas: Vol. 5 No. 1 (2025): IJERA
- Jose P Pittappillil, Midhun Mohan, Nimisha Nigel, Nitin Sunil Thomas, Driving Agricultural Innovation: A Review of Technological Advancements in Smart Farming , International Journal on Emerging Research Areas: Vol. 4 No. 1 (2024): IJERA
- Manjima M A, Soumya Anand, Partial Replacement of bitumen by Plant Polymer Lignin in Bituminous Pavement , International Journal on Emerging Research Areas: Vol. 3 No. 1 (2023): IJERA
- Amith Bino, Don Peter Joseph, Sreehari P, Anchal J Vattakunnel, Revolutionizing Nutritional Management Through Food Scanning And Object Detection: A New Android Application For Adults , International Journal on Emerging Research Areas: Vol. 3 No. 1 (2023): IJERA
- Kaveri S, Pooja Satheesh, Kesiya Susan John, Reubel K Wilson, Dr. Jacob John, Predictive Maintenance of Machines Using IoT and Machine Learning , International Journal on Emerging Research Areas: Vol. 4 No. 2 (2024): IJERA
- Rhea Maria James, Richy Sara George, Sayooj Kumar M, Nihal Muhammed Ayoob, Shan Krishna, Tintu Alphonsa Thomas, A Machine Learning Framework for Tumour Classification Using Transcriptomic and Multi-Omics Datasets , International Journal on Emerging Research Areas: Vol. 6 No. 1 (2026): IJERA
- Arun T S, Bhavana Rajesh Pillai, Devapriya L, Javaid Iqbal, Sreekala K S, Automated Hydroponics for Agricultural Applications , International Journal on Emerging Research Areas: Vol. 3 No. 1 (2023): IJERA
- Sumi Joseph, Diana George, Ruthi Namburi, Dhanya Prathap, Artificial Intelligence in Opthamology:A study on different AIML approaches for Glaucoma prediction , International Journal on Emerging Research Areas: Vol. 6 No. 1 (2026): IJERA
You may also start an advanced similarity search for this article.
