Authors :
Dr. Granty Regina Elwin; Kiruthika E; Paranitharan M; Raghav Kumar K M
Volume/Issue :
Volume 9 - 2024, Issue 3 - March
Google Scholar :
https://tinyurl.com/bdd7mh58
Scribd :
https://tinyurl.com/khcknpta
DOI :
https://doi.org/10.38124/ijisrt/IJISRT24MAR717
Abstract :
With the increase of fame for online food
platforms as well as a broad range of culinary choices,
there has been a need for stronger and more correct food
recommendation systems that can help users in
discovering new and fascinating foods that are tailored to
their individual tastes. This paper presents an innovative
design of constructing a recommendation system by
utilizing both content-based approach and collaborative
filtering techniques. Our system applies machine learning
algorithms to examine user preferences as well as dish
attributes with personalized recommendations based on it
thereby increasing satisfaction levels and overall
engagement rates. The experimental results we provide
herein demonstrate the efficacy and accuracy of our
hybrid filtering method and prove its ability to transform
how individuals find pleasure in eating.
Keywords :
User-Item Matrix, Vectorization, Cosine Similarity Matrix.
With the increase of fame for online food
platforms as well as a broad range of culinary choices,
there has been a need for stronger and more correct food
recommendation systems that can help users in
discovering new and fascinating foods that are tailored to
their individual tastes. This paper presents an innovative
design of constructing a recommendation system by
utilizing both content-based approach and collaborative
filtering techniques. Our system applies machine learning
algorithms to examine user preferences as well as dish
attributes with personalized recommendations based on it
thereby increasing satisfaction levels and overall
engagement rates. The experimental results we provide
herein demonstrate the efficacy and accuracy of our
hybrid filtering method and prove its ability to transform
how individuals find pleasure in eating.
Keywords :
User-Item Matrix, Vectorization, Cosine Similarity Matrix.
