cases on association rules analysis of customer behavior and service modeling
TRANSCRIPT
Cases on Association Rules
Analysis of Customer Behavior and Service
Modeling
CASE 1:
Icecream -Target Brands & Variables
1. Icecream -Target Brands & Variables1. Icecream -Target Brands & Variables
Brands
Gusttimo
Baskin Robbins
Natture
Haagen-dazs
Etc.
Brands Varaibles
Taste
Price
Mood
Distance
Brand Image
Service
Rumor
Variables
• Why do you visit there?• ①.Taste ②.Price ③.Mood ④ .Distance
⑤. Image ⑥. Service ⑦. Rumor
2. Questionnaires2. Questionnaires
• Where do you visit the most for ice cream?• ①.Gusttimo ②.Baskin Robbins ③.Natture ④.H
aagen-daz ⑤. Red Mango ⑥. Palazzo ⑦.etc
• Choose the number below according to your value level when you choose to eat ice cream
3. Questionnaire Method3. Questionnaire Method
Classification
Not important-------------Most important
Taste (1) (2) (3) (4) (5) (6) (7)Price (1) (2) (3) (4) (5) (6) (7)Mood (1) (2) (3) (4) (5) (6) (7)
Distance (1) (2) (3) (4) (5) (6) (7)Image (1) (2) (3) (4) (5) (6) (7)Service (1) (2) (3) (4) (5) (6) (7)Rumor (1) (2) (3) (4) (5) (6) (7)
4. Average value on each variables4. Average value on each variables
0
1
2
3
4
5
6
7
Average
5. Derive rules by using Magnum Opus 5. Derive rules by using Magnum Opus
Mood -> Red Mango [Coverage=0.025 (4); Support=0.019 (3); Strength=0.750; Lift=4.11; Leverage=0.0143 (2.3); p=0.0195]
Red Mango -> Mood [Coverage=0.182 (29); Support=0.019 (3); Strength=0.103; Lift=4.11; Leverage=0.0143 (2.3); p=0.0195]
Baskin -> distance [Coverage=0.390 (62); Support=0.145 (23); Strength=0.371; Lift=2.03; Leverage=0.0735 (11.7); p=1.28E-006]
distance -> Baskin [Coverage=0.182 (29); Support=0.145 (23); Strength=0.793; Lift=2.03; Leverage=0.0735 (11.7); p=1.28E-006]
Gustimo -> Taste [Coverage=0.258 (41); Support=0.233 (37); Strength=0.902; Lift=1.56; Leverage=0.0835 (13.3); p=3.18E-007]
Taste -> Gustimo [Coverage=0.579 (92); Support=0.233 (37); Strength=0.402; Lift=1.56; Leverage=0.0835 (13.3); p=3.18E-007]
CASE 2: Lotte World
Contents 1
1.Problem Definition & constraints
2.Phases
3.Alternatives 1. Using RFID
2. Exit Poll
4. Result Example
5. Effectiveness & application
Problem Definition & Phases 2
Problem Definition
- Attraction locating : avoid conflict between target segments - inefficient customer route Lower customer satisfaction
Constraints
- Attraction re-location : Impossible
1. Data Mining2. Using Model3. Finding efficient customer route & Promotion strategy4. Max (Customer satisfaction)
Phases
HOW – Association Rules 3
Association RulesIndicating & Choice of Alternatives
1. Using RFID
- Clear understanding about customer’s moving route, location, time - Technical Difficulty, and Heavy cost
2. Exit Poll
- Easy application - Light cost - Limit in data : quantity, quality
Survey : Let customers to check all facilities they rode
Make Market-Basket
Association Rules Analysis : based on Market-Basket
Survey Example 4
For Lotteworld Adventure For Magic IslandAdventure of Sinbad ( ) Atlantis ( )Spain Pirate Ship ( ) Gyro Drop ( )Frog Hooper ( ) Gyro Swing ( )Marry-go-round ( ) Bunge Drop ( )Crazy Bumper Car ( ) Comet Express ( )Kids Bumper car ( ) Marry-go-Round 3 ( )Ball Battle ( ) Sky Surfing ( )Flume Ride ( ) Bumper car ( )Giant Roop ( ) Ghost House ( )Marry-go-round 2 ( ) Castle Music Show ( )Illusion Odyssey ( ) Fantasy Dream ( )Out-Law ( ) Automoblile Racing ( )4D Movies ( ) Kingdom of Children ( )Magic Theater ( ) EureKa ( )Puppet Theater ( ) Geneve Excursion Ship ( )French Revolution ( ) Lake Boat ( )Jungle Adventure ( )World Monorail ( )Rage of Parao ( )Balloon Travel ( )dynamic Theater ( )Animal Theater ( )Garden Stage Concert ( )Street Concert ( )Parade ( )
※ Mark Attractions that you rode today
Basic information
1.gender
2.age
3.Marriage
4.Children
5.Age of Children
6.Place of
Residence
7.others
Result Example & Applications 5
1. Student (age 12~18)
- P(Gyro drop Atlantis) : 70%
2. Parents with Little children
- P(Marry-go-Round Kids Bumpercar) : 60%
We will be able to check : Who is using what kind of facilities
Finding Effective Route
Making Promotion StrategyLocate extra store at specific
customer’s route
Result Example
Applications
CASE 3:Gmart case
Data Collection
: Gmart located at Yongsan
- Customer data POS data from daily transaction
- Location Chung-pa dong, Yongsa,, Seoul
- Period 2005. 9. 1 ~ 2005. 12. 7.
- Number of data 1,334 cases
- Contents in the data POS fields names(date, time, POS manager, receipt number, product name , quantity, amount, classification)
- G mart system screen -
Data
Cookies, MilkYogurt ,Frozen foolBear, Cookies, CoffeeMilk, Water. . ..
.
Extracted Association RuleWateris associated with Cookieswith strength = 0.500coverage = 0.002: 2 cases satisfy the LHSsupport = 0.001: 1 case satisfies both the LHS and the RHSlift 500.00: the strength is 500.00 times greater than the strength if there
were no associationleverage = 0.0010: the support is 0.0010 (1.0 case) greater than if there
were no association
Wateris associated with Coffee and Newspaperwith strength = 0.500coverage = 0.002: 2 cases satisfy the LHSsupport = 0.001: 1 case satisfies both the LHS and the RHSlift 500.00: the strength is 500.00 times greater than the strength if there
were no associationleverage = 0.0010: the support is 0.0010 (1.0 case) greater than if there
were no association