Scribd
Upload
103 views

1an Intelligent Approach For Food Recipe Rating Prediction Using Machine Learning

This study aims to rate recipes using machine learning algorithms by comparing the performance of classifiers. It analyzes recipe attributes to economically benefit restaurants and help customers choose restaurants based on recipe quality. Existing systems rely on sentiment analysis of reviews, but results may not be accurate. The proposed system applies machine learning algorithms like Naive Bayes, Logistic Regression, and Decision Trees to recipes after preprocessing data to more reliably rate recipes. This focuses on applying advanced deep learning for food science and identifying important predictors for conditions like obesity.

Uploaded by

IT SEM-V
Copyright
© © All Rights Reserved
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
103 views

1an Intelligent Approach For Food Recipe Rating Prediction Using Machine Learning

This study aims to rate recipes using machine learning algorithms by comparing the performance of classifiers. It analyzes recipe attributes to economically benefit restaurants and help customers choose restaurants based on recipe quality. Existing systems rely on sentiment analysis of reviews, but results may not be accurate. The proposed system applies machine learning algorithms like Naive Bayes, Logistic Regression, and Decision Trees to recipes after preprocessing data to more reliably rate recipes. This focuses on applying advanced deep learning for food science and identifying important predictors for conditions like obesity.

Uploaded by

IT SEM-V
Copyright
© © All Rights Reserved
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 3

An Intelligent Approach for Food Recipe Rating Prediction Using Machine

Learning
In recent times, there are many studies and systems which deal with restaurant
rating or individual food rating but rating a recipe using Artificial Intelligence is
rare. This study aims to rate recipes based on different attributes using different
Machine Learning algorithms. It compares the performance of different classifiers
in rating a recipe based on different performance criterion. This can be
economically beneficial to restaurants by helping them improve their recipes and
getting more customers. It can also be used in a more personal level to improve
household recipes and for the customers of restaurants to decide which restaurant
is better for a specific dish based on how good their recipe is.
EXISTING SYSTEM:
Food tasting and rating is becoming more and more popular everywhere which is
clearly visible in different online and social media platforms. Food quality can be
assessed from different points of view. In this method, we calculate the sentiment
score by evaluating the ratio of Count of Positive and negative points of star
ratings and those results are not up to the mark and some cases it can be re-written
by the company’s by themselves .

DISADVANTAGES OF EXISTING SYSTEM:


 irrelevant results are more present in the results .
 sentiment of the review are not reaching the truth.
Algorithm: knn
PROPOSED SYSTEM:
If someone is interested in a particular dish or recipe it becomes difficult for them
to check how good it is. Different restaurants may also make the same dish using
different recipes. So this system can help them see how their dish is rated
compared to others. after discarding unnecessary and irrelevant review in the
previous steps, scraping data, dropping missing observations and transforming it
into a proper data-set, the total data was divided into 2 sets, keeping 80% data in
the training set and 20% data in the test set. After that, different machine learning
algorithms i.e Naive Bayes, Logistic Regression, K Nearest Neighbour, Decision
Tree, Random Forest, Support vector Machine were applied to find training and
testing accuracy. It compares the performance of different classifiers in rating a
recipe based on different performance criterion.
ADVANTAGES OF PROPOSED SYSTEM:
 applying deep learning on food science. It focuses on applying deep learning
as an advanced data mining tool for food sensory research. Their survey
indicates that deep learning in food science outperforms conventional
machine learning algorithms
 The ML algorithms are used to find the most important predictor that
separates obese subjects from the control.

Algorithm: Naive Bayes, Logistic Regression, Decision Tree, Random Forest,


Support vector Machine.

SYSTEM REQUIREMENTS:
HARDWARE REQUIREMENTS:
 System : Intel Core i3.
 Hard Disk : 1TB.
 Monitor : 15’’ LED
 Input Devices : Keyboard, Mouse
 Ram : 8GB.

SOFTWARE REQUIREMENTS:

 Operating system : Windows 10.


 Coding Language : Python
 Tool : PyCharm, Visual Studio Code
 Database : SQLite

REFERENCES:
Ismam Hussain Khan; Md Habib Ullah Khan; Md Mamun Howlader, ‘An
Intelligent Approach for Food Recipe Rating Prediction Using
MachineLearning’, Date of Conference: 06-07 April 2021Date Added
toIEEE Xplore: 11May 2021Information: Electronic ISBN:978-1-6654-1511-8
Print on Demand(PoD) ISBN:978-1-6654-3041-
8DOI: 10.1109/CAIDA51941.2021.9425031

You might also like