A comparative sales forecast study between supervised and unsupervised learning algorithm on restaurant / Azhar Tamby

Tamby, Azhar (2006) A comparative sales forecast study between supervised and unsupervised learning algorithm on restaurant / Azhar Tamby. Student Project. Faculty of Information Technology and Quantitative Sciences, Shah Alam. (Unpublished)

[img] Text
PPb_AZHAR TAMBY CS 06_5 1.pdf

Download (59kB)

Abstract

In this research, there are two algorithm of neural network will be used. It is coming from supervised and unsupervised learning algorithm. The Kohonen Self Organizing Map represents the unsupervised and Backpropagation represent the supervised. There will be a comparative study between these two algorithms with restaurant sales forecast as a scope. Some restaurant activities will be the input for the architecture to make a sales forecast. Each of the algorithm will used all the similar value including the learning rate in this research in order to make the comparison.

Item Type: Monograph (Student Project)
Creators:
CreatorsID Num.
Tamby, AzharUNSPECIFIED
Subjects: H Social Sciences > HF Commerce > Marketing > Marketing research. Marketing research companies. Sales forecasting
Q Science > QA Mathematics > Instruments and machines > Electronic computers. Computer science > Neural networks (Computer science)
Q Science > QA Mathematics > Instruments and machines > Electronic computers. Computer science > Neural networks (Computer science)

Q Science > QA Mathematics > Instruments and machines > Electronic computers. Computer science > Algorithms
Q Science > QA Mathematics > Instruments and machines > Electronic computers. Computer science > Algorithms

T Technology > TX Home economics > Restaurants, cafeterias, tearooms, etc.
Divisions: Faculty of Information Technology and Quantitative Sciences
Item ID: 1386
Uncontrolled Keywords: Sales forecast, Learning algorithm, Neural networks, Restaurants
Last Modified: 23 Feb 2017 06:45
Depositing User: Staf Pendigitalan 1
URI: http://ir.uitm.edu.my/id/eprint/1386

Actions (login required)

View Item View Item

Downloads

Downloads per month over past year