CAR-RECOMMENDATION-SYSTEM-1-1 (2)

CAR RECOMMENDATIO N SYSTEM Analysis... Duong Anh Quang Obijiaku Calisstus Chisom Nguyen Thi Phuong Hang... MOTIVATION AND PURPOSE REPERTORY GRID ANALYSIS FUZZY COGNITIVE MAP... Motivatio

CAR

RECOMMENDATIO

N SYSTEM

Analysis

Duong Anh Quang

Obijiaku Calisstus Chisom

Nguyen Thi Phuong Hang

MOTIVATION AND PURPOSE

REPERTORY GRID

ANALYSIS

FUZZY COGNITIVE MAP

Motivation and purpose

• The number of vehicles in global market

is increased

• Many cars with similar features get into market

 People will be confused on what to choose

We built a car recommend system

based on the elements and constructs.

Repertory grid

1 Youtube videos drive.com

.au nada.com telegraph .co.uk edmunds. com

Car company website

Friend recomme ndation Personal taste Showroo m 7

Detailed

Used by most

Reliable Info

Widely

Satisfactory

Easy to find

Able to

Feedback

Element Analysis (Pearson

Correlation)

youtube 1 0.26 -0.02 0.38 -0.46 0.31 0 -0.28 -0.30 drive.com 2 0.44 0.12 -0.12 0.54 -0.24 -0.04 -0.4

telegraph.co.u

car company

website

showroom 9

Element Analysis (Distance

Euclidean)

youtube 1 8.0 9.27 7.14 6.56 7.42 8.89 11.75 9.95

telegraph.co.u

car company

website

showroom 9

Contruct Analysis (Pearson

Correlation)1 2 3 4 5 6 7 8 9 10

Detailed

Explaintion 1 0.44 -0.05 0.04- 0.44 0.40 -0.14 -0.09 0 0.05 Used by most

people 2 -0.48 0.54 0.25 0.20 0.11 0.05 0.15 0.40 Reliable

Widely

Satisfactory

Easy to find

Easy

Able to

recommend

Feedback

functionality 10

Fuzzy Cognitive Map

Cause/

Effect

User Numbe r

Technolog

Concept

Value

initializati

on

FCM Diagram

User Number UX

UI

User data Car Data

Service Technolog

y

• At is the value of concept at timestep t

• W0 is the matrix of casual relationship.

• K2j is the weight of previous concept value at time t-1

• A t-1 is the value of concepts at timestep t-1

• K2j = 0.5

Sigmoid

Implementatio n

concepts value at different

stages

Concepts Value

1 0.776 0.55 0.636 0.747 0.532 0.613 0.701

1 0.835 0.568 0.662 0.76 0.593 0.629 0.821

3 0.845 0.571 0.669 0.767 0.601 0.632 0.838

4 0.847 0.571 0.67 0.769 0.602 0.633 0.841

5 0.848 0.571 0.67 0.77 0.602 0.633 0.842

=> User number and user data is the most important concept in the car recommendation system