Association Discovery. Janjao Mongkolnavin Department of Statistics Faculty of Commerce and Accountancy Chulalongkorn University

Size: px
Start display at page:

Download "Association Discovery. Janjao Mongkolnavin Department of Statistics Faculty of Commerce and Accountancy Chulalongkorn University"

Transcription

1 Association Discovery Janjao Mongkolnavin Department of Statistics Faculty of Commerce and Accountancy Chulalongkorn University

2 Outline Market basket analysis Association rules Support-confidence framework Sequential analysis using association rules Dependent framework Understanding associations The cross-purchase skew methodology 2

3 Market Basket Analysis (1) 3

4 Market Basket Analysis (2) Market basket analysis uses the information about what customers purchase to provide insight into who they are and why they make certain purchases. Market basket analysis provides insight into the merchandise by telling us which products tend to be purchased together and which are most amenable to promotion. 4

5 Market Basket Analysis (3) This information can be used to suggest new store layouts, to determine which product to put on special, to indicate when to issue coupons. When this data tie to individual customers through a loyalty card or web registration, it becomes even more valuable. 5

6 Example of Output If customers buy product A they also tend to buy product B, x% of the time The word product can be extended to attributes,such as demographic, promotion, seasonal, and they can be extended to a group of products, such as all dairy products. Applications of basket analysis include cross-marketing, store layout, catalog design, product pricing and promotion. 6

7 Association Rules (1) Association rules represent patterns in the data without a specified target. 7

8 Association Rules (2) Although its roots are in analyzing pointof-sale transactions, association rules can be applied outside the retail industry such as Items purchased on a credit card Optional services purchased by telecommunication customers (call waiting, call forwarding) Banking services used by retail customers Unusual combinations of insurance claims 8

9 Building Association Rules (1) 9

10 Building Association Rules (2) Choose the right set of items Generate rules by deciphering the counts in the co-occurrence matrix Overcome the practical limits imposed by thousand or ten of thousand of items 10

11 Building Association Rules: Choose the Right Set of Items (1) 11

12 Building Association Rules: Choose the Right Set of Items (2) One way to compromise is to use more general items initially, then to repeat the rule generation on more specific items. The desired complexity of the rules also determines how specific or general the items should be. The appropriate level depends on its importance for producing actionable results eg. its frequency in the data. 12

13 Virtual Items Virtual items do not appear in the product hierarchy of the original items, because they cross product boundaries. Virtual items may include information about whether the purchased was made with cash or a credit card, the day of week or the time of the day the transaction occurred. 13

14 Anonymous - Identified For anonymous transactions, the only information is the date and time, the location of the store, the cashier, the items purchased, any coupons redeemed, and the amount of change. For identified transactions, we have more information on customers and their behavior over time such as demographic. These information can be incorporated into association rule by treated as virtual items. 14

15 Support-Confidence Framework The goal is to extract association of the form If A then B by using support and confidence. Support is define as the minimum percentage of transactions in the training set containing A and B. Confidence is defined as the minimum percentage of those baskets containing A that also contain B. 15

16 Support-Confidence Framework For example, suppose the training set contains 1,000,000 transactions (records), 10,000 of those transactions contain both A and B, the support of the association if A then B is 10,000 / 1,000,000 = 1%. If 50,000 of the transactions contain A and 10,000 out of those 50,000 also contain B, then the association if A then B has a confidence of 10,000 / 50,000 = 20% Thus confidence is the conditional probability of B given A ( P(B A) ). 16

17 Example When a customer buys a shirt, in 70% of cases, he or she will also buy a tie. We find this happen in 13.5% of all purchases. From this sentence, what is the percentage of support? What is the percentage of confidence? 17

18 Example Basketid A B C D E T T T T T T T T T T

19 Example The frequent sets for frequency threshold 0.4 are {A}, {B}, {C}, {D}, {AC}, and {BC}. Confidence for rule A -> C = 4 / 6 Confidence for rule B -> C = 5 / 5 19

20 Note on Confidence (1) Note that confidence alone does not distinguish whether the association between A and B is random or not. It has to be used together with other probabilities because we are interested in finding association between A and B where the occurrence of B is different from what would be expected by random chance. 20

21 Note on Confidence (2) For a statement When customers buy bread at a grocery store, 30% of the time they also buy milk, if 30% of all transactions in this store contain milk. Do you think this statement useful? 21

22 Note on Confidence (3) For example, it would be interesting to find that milk occurs 50% in all baskets containing coffee, which means there is a 20% lift of milk above the expected random occurrence of it. 22

23 Note on Support Generally, support is used to weight the significance of groups of transactions. Simple example will be we may ignore transactions with low support, or in other word, transactions that occur infrequently. However, sometimes, low-supported transactions can be useful in the discovery. 23

24 A Basic Algorithm 1. Create a set of one-dimensional columns whose frequency of occurrence are higher than the specified support. 2. Create a set of two-dimensional columns that are the combinations of the columns from (1) and test their support. 3. Repeat until there is no combination of columns satisfying the specified support. 24

25 What They Tell Us? (1) Rules based on high support and confidence factors represent a higher degree of relevance than rules with low support and confidence factors. However, if the support and confidence factors are too high, association rules may not be discovered. 25

26 What They Tell Us? (2) If the factors are too low, there will be many possible combinations of product associations, which is not what we want. 26

27 Sequential Analysis Using Association Rules Normally, association rules find things that happen at the same time. In order to use time series, the transaction data must have two additional features: A timestamp or sequencing information to determine when transactions occurred relative to each other Identifying information, such as account number or customer id that identifies different transactions as belonging to the same customer. 27

28 Sequential Analysis Using Association Rules: Procedure All items purchased by a customer are treated as a single order and each item retains the timestamp indicating when it was purchased. The process is the same for finding groups of items that appear together. To develop the rules, only rules where the items on the left-hand side were purchased before items on the right-hand side are considered. 28

29 Dependent Framework The Dependence Framework considers only transactions whose percent of cooccurrence is significantly different from random chance. In Statistics, the two events are independent if the probability of their cooccurrence is the same as the product of the probabilities of each event occurring individually. Eg. Probability(AB) = Probability(A) * Probability(B) 29

30 Dependent Framework: Example Both Coke and Pepsi occur separately in 50% of all baskets, and we expected that they should occur together 25% of all baskets by random chance, but the actual percent of cooccurrence was 0.01%. Thus, Expected(Coke + Pepsi together) = 25% Actual(Coke + Pepsi together) = 0.01% The difference between the two probabilities is large, so we assume that Coke and Pepsi are not independent. 30

31 Dependent Framework: Test the Difference In order to conclude whether two events are independent from each other, we need to test whether the difference between the expected co-occurrence and the actual co-occurrence are statistically significant. We can use the Chi-Squared test X [ ExpectedCoOccurrence ActualCoOccurrence = ExpectedCoOccurrence 2 2 ] 31

32 Dependent Framework: Test the Difference Note that the Chi-Squared test measures deviation from the expected random cooccurrence. It is equal zero if the deviation from random co-occurrence is zero, and it is greater than zero if the events are dependent. This statistic has a chi-square distribution. Thus, we can compare it against the Chi- Squared table and obtain a p value that will tell us the confidence level of our conclusion. 32

33 Beyond Statistical Dependence (1) We can better understand the dependence between two events by looking at its Impact and Lift. Impact is the ratio of the actual co-occurrence divided by the expected co-occurrence: Im pact = ActualCoOccurrence ExpectedCoOccurrence The impact is equal to one if the products are independent, and is different from one if the product are dependent. 33

34 Beyond Statistical Dependence (2) For example Impact(Coke+Pepsi) = 0.01/25 = which indicates that Coke and Pepsi are very dependent. Lift of event A on event B is defined as the difference between the expected and the actual co-occurrences of A and B divided by the frequency of A: [ ActualCoOccurrence ExpectedCoOccurrence] Lift( AonB) = FrequencyofOccurrenceofA 34

35 Beyond Statistical Dependence (3) Note that the value lift is between -1 and 1. The lift is close to zero if the items are independence. It is positive if the items are positively dependent. It is negative if the items are negatively dependent. 35

36 Beyond Statistical Dependence (4) For example: Life(Coke on Pepsi) = ( )/0.50 = This negative lift implies that Coke and Pepsi tend not to be in the same baskets. 36

37 Understanding Associations (1) When two events are negatively associated, they can either compete with each other in the same market segment, or they serve different market segments and they do not compete. 37

38 Understanding Associations (2) Likewise, two events can be positively associated because they complement each other or a third product complement them both. This distinct reasons can lead to very different marketing strategies. 38

39 The Cross-Purchase Skew Methodology (1) In this methodology, we further investigate the dependence association by using the third event (C) to pair with event A and B, and see if they show the same co-occurrence percentage. If they show the same co-occurrence percentage (no cross purchase skew), they confirm the assumption about the association between A and B. 39

40 The Cross-Purchase Skew Methodology (2) If they show different co-occurrence percentage (cross purchase skew), the association between A and B may have different explanation. 40

41 The Cross-Purchase Skew Methodology: Examples (1) Suppose that the orange juice and soda repel each other, leading to suspect that they may be substitutes. The investigation reviews that they exhibit cross-purchase skew when compared against whole-wheat bread. This reveals that A and B are not substitutes and do not compete. 41

42 The Cross-Purchase Skew Methodology: Examples (2) For example, It might be that healthy food, such as whole-wheat bread, tend to be purchased more often with orange juice than with soda. On the other hand, in the case of Coke and Pepsi, you may find little or no cross-purchase skew when pairing them with the third products. It may reveal that Coke and Pepsi are substitutes that compete in the same market. 42

43 Effective Basket Analysis Once groups of events that exhibit statistically significant non-random associations are found, should further analyze the cause of their non-random associations. 43

44 Q & A

Intelligent Decision Support Systems

Intelligent Decision Support Systems Intelligent Decision Support Systems (Case Study 6 Market Basket Analysis ) Anna Gatzioura, Miquel Sànchez i Marrè Course 2017/2018 https://kemlg.upc.edu Market Basket Analysis (1) INPUT: list of purchases

More information

Retail Product Bundling A new approach

Retail Product Bundling A new approach Paper 1728-2018 Retail Product Bundling A new approach Bruno Nogueira Carlos, Youman Mind Over Data ABSTRACT Affinity analysis is referred to as Market Basket Analysis in retail and e-commerce outlets

More information

EE627A: Market Basket Analysis Using Association Rules

EE627A: Market Basket Analysis Using Association Rules EE627A: Market Basket Analysis Using Association Rules Rensheng Wang Stevens Institute of Technology rwang1@stevens.edu July 29, 2015 1 / 27 Market Basket Analysis To identify associations among items

More information

Session 15 Business Intelligence: Data Mining and Data Warehousing

Session 15 Business Intelligence: Data Mining and Data Warehousing 15.561 Information Technology Essentials Session 15 Business Intelligence: Data Mining and Data Warehousing Copyright 2005 Chris Dellarocas and Thomas Malone Adapted from Chris Dellarocas, U. Md. Outline

More information

ASSOCIATION AND SEQUENCING

ASSOCIATION AND SEQUENCING ASSOCIATION AND SEQUENCING KEYS TO SUCCESSFUL MARKET BASKET ANALYSIS AND WEB MINING Until recently, association and sequencing were often overlooked. Many data mining products often omitted one or both

More information

Case studies in Data Mining & Knowledge Discovery

Case studies in Data Mining & Knowledge Discovery Case studies in Data Mining & Knowledge Discovery Knowledge Discovery is a process Data Mining is just a step of a (potentially) complex sequence of tasks KDD Process Data Mining & Knowledge Discovery

More information

Hospitality user guide

Hospitality user guide Hospitality user guide V1.1 Table of contents ABOUT THIS GUIDE 4 Overview 4 Logging in 5 Start of day 6 ORDERS 6 Orders 6 Taking a new order 7 Take-out orders for delivery or collection 8 Adding extra

More information

Problem Score Problem Score 1 /12 6 /12 2 /12 7 /12 3 /12 8 /12 4 /12 9 /12 5 /12 10 /12 Total /120

Problem Score Problem Score 1 /12 6 /12 2 /12 7 /12 3 /12 8 /12 4 /12 9 /12 5 /12 10 /12 Total /120 EE103/CME103: Introduction to Matrix Methods October 22 2015 S. Boyd Midterm Exam This is an in-class 80 minute midterm. You may not use any books, notes, or computer programs (e.g., Julia). Throughout

More information

Modelling buyer behaviour - 2 Rate-frequency models

Modelling buyer behaviour - 2 Rate-frequency models Publishing Date: May 1993. 1993. All rights reserved. Copyright rests with the author. No part of this article may be reproduced without written permission from the author. Modelling buyer behaviour -

More information

Exam #1 Time: 1h 15m Date: 9 July Instructor: Brian B. Young. Multiple Choice. 2 points each

Exam #1 Time: 1h 15m Date: 9 July Instructor: Brian B. Young. Multiple Choice. 2 points each Economics 211 Macroeconomic Principles Exam #1 Time: 1h 15m Date: 9 July 2013 Name The value of this exam is 100 points. Instructor: Brian B. Young Please show your work where appropriate! Multiple Choice

More information

Machine learning mechanisms in modern Omnichannel marketing and sales.

Machine learning mechanisms in modern Omnichannel marketing and sales. Machine learning mechanisms in modern Omnichannel marketing and sales. Currently, companies operating in retail must face a very competitive market. They very often set their goal at gaining a high number

More information

Exam 1. Price $ per minute $.55 $.30 $.25 $.05. Figure 1. a) 4 b) 5 c) d) 11 e) none

Exam 1. Price $ per minute $.55 $.30 $.25 $.05. Figure 1. a) 4 b) 5 c) d) 11 e) none ECONOMICS 10-008 Dr. John Stewart September 24, 2002 Exam 1 Instructions: Mark the letter for your chosen answer for each question on the computer readable answer sheet using a No.2 pencil. Note =1, b)=2

More information

KROGER AND PERSONALIZATION: A GROCERY RETAILER BECOMING A MEDIA PLAYER?

KROGER AND PERSONALIZATION: A GROCERY RETAILER BECOMING A MEDIA PLAYER? KROGER AND PERSONALIZATION: A GROCERY RETAILER BECOMING A MEDIA PLAYER? 2018 KROGER ALWAYS STARTS WITH THE CUSTOMER 2,800 STORES IN 35 STATES 60MM+ Households 1 OUT OF 2 HOUSEHOLDS IN THE US Confidential

More information

Exam #1 Time: 1h 15m Date: 4 or 5 September Instructor: Brian B. Young. Multiple Choice. 2 points each

Exam #1 Time: 1h 15m Date: 4 or 5 September Instructor: Brian B. Young. Multiple Choice. 2 points each Economics 211 Macroeconomic Principles Exam #1 Time: 1h 15m Date: 4 or 5 September 2013 Name The value of this exam is 100 points. Instructor: Brian B. Young Please show your work where appropriate! Multiple

More information

Case studies in Data Mining & Knowledge Discovery

Case studies in Data Mining & Knowledge Discovery Case studies in Data Mining & Knowledge Discovery Knowledge Discovery is a process Data Mining is just a step of a (potentially) complex sequence of tasks KDD Process Data Mining & Knowledge Discovery

More information

Uncover possibilities with predictive analytics

Uncover possibilities with predictive analytics IBM Analytics Feature Guide IBM SPSS Modeler Uncover possibilities with predictive analytics Unlock the value of data you re already collecting by extracting information that opens a window into customer

More information

[GCSE COMMERCE TOPIC 2 REVISION NOTES]

[GCSE COMMERCE TOPIC 2 REVISION NOTES] Services of retailer to consumer Retailer provides goods at right time and place Provides after sales and customer service Retailer makes sure that the quality is maintained Provides credit to customers

More information

Fresh Start: A Fresh Perspective on Mobile Loyalty Abierto Networks Fresh Start Convenience Stores Loyalty Program Case Study

Fresh Start: A Fresh Perspective on Mobile Loyalty Abierto Networks Fresh Start Convenience Stores Loyalty Program Case Study Fresh Start: A Fresh Perspective on Mobile Loyalty ----- Abierto Networks Fresh Start Convenience Stores Loyalty Program Case Study - A PUBLICATION OF ABIERTO NETWORKS - Choosing the right promotions is

More information

MEASURING REAL-TIME PREDICTIVE MODELS. 1. Introduction

MEASURING REAL-TIME PREDICTIVE MODELS. 1. Introduction MEASURING REAL-IME PREDICIVE MODELS SAMUEL SEINGOLD, RICHARD WHERRY, AND GREGORY PIAESKY-SHAPIRO Abstract. In this paper we examine the problem of comparing real-time predictive models and propose a number

More information

M.Tech. IN ADVANCED INFORMATION TECHNOLOGY - SOFTWARE TECHNOLOGY (MTECHST)

M.Tech. IN ADVANCED INFORMATION TECHNOLOGY - SOFTWARE TECHNOLOGY (MTECHST) No. of Printed Pages : 8 I MINE-0221 M.Tech. IN ADVANCED INFORMATION TECHNOLOGY - SOFTWARE TECHNOLOGY (MTECHST) Time : 3 hours Note : (i) (ii) (iii) (iv) (v) Term-End Examination December, 2014 MINE-022

More information

Moving the Needle (and making it stick) Supply Chain Metrics that Drive Financial & Operational Improvement

Moving the Needle (and making it stick) Supply Chain Metrics that Drive Financial & Operational Improvement Moving the Needle (and making it stick) Supply Chain Metrics that Drive Financial & Operational Improvement Dave Brooks, Sr. Director, Software AG Jim Waites, Managing Director, IDS Scheer June 23, 2010

More information

Andy consumes baseball cards and football cards.

Andy consumes baseball cards and football cards. Economics 301 - Homework 3 Fall 006 Stacy Dickert-Conlin Name Due: September 8, at the start of class Three randomly selected questions will be graded for credit. All graded questions are worth 10 points.

More information

AP Microeconomics Chapter 3 Outline

AP Microeconomics Chapter 3 Outline I. Learning Objectives In this chapter students should learn: II. Markets III. Demand A. What demand is and how it can change. B. What supply is and how it can change. C. How supply and demand interact

More information

Predicting Loyal Customers for Sellers on Tmall to Increase Return on Promoting Cost

Predicting Loyal Customers for Sellers on Tmall to Increase Return on Promoting Cost Predicting Loyal Customers for Sellers on Tmall to Increase Return on Promoting Cost Wendy Huang Yu-Chih, Shih Jessy Yang Zoe Cheng BADM Team 9 Summary Sellers on E-commerce platform sometimes run big

More information

Creation of a PAM matrix

Creation of a PAM matrix Rationale for substitution matrices Substitution matrices are a way of keeping track of the structural, physical and chemical properties of the amino acids in proteins, in such a fashion that less detrimental

More information

Application of Data Mining Technique in Business to Consumer Electronic Commerce

Application of Data Mining Technique in Business to Consumer Electronic Commerce 2017 3rd International Conference on Social Science and Technology Education (ICSSTE 2017) ISBN: 978-1-60595-437-0 Application of Data Mining Technique in Business to Consumer Electronic Commerce Jing

More information

THE STATE OF CUSTOMER DEVOTION IN RETAIL PART TWO

THE STATE OF CUSTOMER DEVOTION IN RETAIL PART TWO THE STATE OF CUSTOMER DEVOTION IN RETAIL PART TWO A QUICK RECAP: PART ONE... THE OBJECTIVE We were intrigued to discover how customer s devotion to retailers is influenced by loyalty strategies. THE METHODOLOGY

More information

McBride ECON Formative Quiz 4.1 and 4.2

McBride ECON Formative Quiz 4.1 and 4.2 Name: Class: _ Date: _ ID: A McBride ECON Formative Quiz 4.1 and 4.2 Multiple Choice Identify the choice that best completes the statement or answers the question. 1. Which is an example of the law of

More information

Elasticity. Demand Curve. Quantity of units

Elasticity. Demand Curve. Quantity of units Cooleconomics.com Principles of Economics Elasticity Contents: Demand and steepness Supply and steepness Elasticity introduction price elasticity of demand price elasticity of supply income elasticity

More information

This exam contains 9 pages (including this cover page) and 14 questions. Check to see if any pages are missing.

This exam contains 9 pages (including this cover page) and 14 questions. Check to see if any pages are missing. ECON 001 Fall 2015 A. Duchene Midterm 1 September 30, 2015 Time Limit: 60 Minutes Name (rint): Recitation Section: Name of TA: This exam contains 9 pages (including this cover page) and 14 questions. Check

More information

Understanding Demand

Understanding Demand Understanding Demand Students will be able to identify characteristics of the law of demand. Students will be able to define and/ or identify the following terms: Law of Demand Substitution Effect Income

More information

THE Marketing Plan. SCORE Chapter 37 Houston, Texas

THE Marketing Plan. SCORE Chapter 37 Houston, Texas THE Marketing Plan SCORE Chapter 37 Houston, Texas 1 Why Plan? Establish direction Identify obstacles Set goals & objectives Take an objective view Communicates owner s ideas - Tells a story 2 Part of

More information

How well targeted are soda taxes?

How well targeted are soda taxes? How well targeted are soda taxes? Pierre Dubois, Rachel Griffith and Martin O Connell Institute for Fiscal Studies Imperial, February 2018 1 / 28 Motivation Sugar consumption is far in excess of recommended

More information

Functional Guide for the Promotion Calculation Engine

Functional Guide for the Promotion Calculation Engine Promotion Calculation Engine Document Version: 1.0 2017-12-01 SAP Customer Activity Repository 3.0 FP2 Typographic Conventions Type Style Example Description Words or characters quoted from the screen.

More information

QuickBooks Online Student Guide. Chapter 10. Inventory

QuickBooks Online Student Guide. Chapter 10. Inventory QuickBooks Online Student Guide Chapter 10 Inventory Chapter 2 Chapter 10 In this chapter, you ll learn how QuickBooks handles inventory. You can use QuickBooks to track the items you keep in inventory

More information

RETAIL MANAGEMENT SOFTWARE SYSTEMS for furniture, design and home furnishings stores

RETAIL MANAGEMENT SOFTWARE SYSTEMS for furniture, design and home furnishings stores RETAIL MANAGEMENT SOFTWARE SYSTEMS for furniture, design and home furnishings stores Manage a large product range, from made-to-order pieces to fast-moving stock items, with LS Retail omni-channel solutions

More information

Estimation Theory. (Exercises)

Estimation Theory. (Exercises) Chapter II Estimation Theory (Exercises) 2. 1. The Annual salary for public school teachers in the US is $32000. The mean salary for a sample of 750 school teachers equals 31895. Identify the population,

More information

Acquire, Convert, Develop and Retain

Acquire, Convert, Develop and Retain Acquire, Convert, Develop and Retain Increasing The Lifetime Value of Your Customers White Paper October 2015 Now Part of CSG How Does Your Company Acquire, Convert, Develop and Retain The Customers You

More information

Submit your scantron and questions sheet

Submit your scantron and questions sheet PRINT YOUR NAME Exam 1 Submit your scantron and questions sheet Version A 1. Scarcity means that A) what we can produce with our resources is greater than our material wants B) resources are unlimited

More information

Data Mining and Knowledge Discovery in Large Databases

Data Mining and Knowledge Discovery in Large Databases Outline We are drowning in data, but we are starving for knowledge Part 2: Clustering - Hierarchical Clustering - Divisive Clustering - Density based Clustering Data Mining and Knowledge Discovery in Large

More information

Cross Functional playbook for Restaurants. An overview of loss prevention methods using Video-Driven Business Intelligence

Cross Functional playbook for Restaurants. An overview of loss prevention methods using Video-Driven Business Intelligence Cross Functional playbook for Restaurants An overview of loss prevention methods using Video-Driven Business Intelligence Loss Preventation Playbook for Restaurants Contents Introducing Envysion 3 Who

More information

How do I become a Rewards member? Simple, either ask to join while you are in the store or visit the Rewards page on our website to sign up.

How do I become a Rewards member? Simple, either ask to join while you are in the store or visit the Rewards page on our website to sign up. Get Rolling And Become A Member Get more out of every purchase you make at David s World Cycle and participating Trek Bicycle Stores. DWC Rewards is a free loyalty program that allows members to earn points

More information

CHAPTER VI FUZZY MODEL

CHAPTER VI FUZZY MODEL CHAPTER VI This chapter covers development of a model using fuzzy logic to relate degree of recording/evaluation with the effectiveness of financial decision making and validate the model vis-à-vis results

More information

Become an Exception Reporting Hero

Become an Exception Reporting Hero Become an Exception ing Hero A guide to take your exception reports to the next level 2013 Envysion, Inc. Page 1 Forward Most retail and restaurant operators collect an overwhelming amount of data from

More information

Nielsen Loyalty driving programs a new vision. ECR Baltic November 2011

Nielsen Loyalty driving programs a new vision. ECR Baltic November 2011 Nielsen Loyalty driving programs a new vision ECR Baltic November 2011 Topic of discussion: Retailers loyalty program Based on: Transaction log combined with Loyalty card data 2 Market Context - Key challenges

More information

STOCK CONTROL RECORDS

STOCK CONTROL RECORDS STOCK CONTROL RECORDS a learning element for staff of consumer cooperatives international labour office, geneva MATCOM 1978-2001 by Urban Strand MATCOM Material and techniques for cooperatives management

More information

L2 Demand. I. Demand Curve. 1. Individual Demand. Example: Helen s demand for lattes.

L2 Demand. I. Demand Curve. 1. Individual Demand. Example: Helen s demand for lattes. L2 Demand Example: Helen s demand for lattes. I. Demand Curve The demand curve shows the relationship between price and quantity demanded. o Quantity demanded means the amount of a good that buyers are

More information

Microsoft Dynamics 365. Factsheet

Microsoft Dynamics 365. Factsheet Factsheet SStrategic Solutions NW 1 Amazing customer experiences through intelligent operations Delivering customer experiences is top of mind for every retail organization, and the use of technology is

More information

Introduction to Analytics Tools Data Models Problem solving with analytics

Introduction to Analytics Tools Data Models Problem solving with analytics Introduction to Analytics Tools Data Models Problem solving with analytics Analytics is the use of: data, information technology, statistical analysis, quantitative methods, and mathematical or computer-based

More information

Chapter 1. QTM1310/ Sharpe. Data and Decisions. 1.1 What Are Data? 1.1 What Are Data? 1.1 What Are Data? 1.1 What Are Data? 1.1 What Are Data?

Chapter 1. QTM1310/ Sharpe. Data and Decisions. 1.1 What Are Data? 1.1 What Are Data? 1.1 What Are Data? 1.1 What Are Data? 1.1 What Are Data? Chapter 1 Data and Decisions Data collected for recording the companies transactions is called transactional data. The process of using transactional data to make other decisions and predictions, is sometimes

More information

Investor Presentation

Investor Presentation Investor Presentation May 2018 Copyright 2018 Quotient Technology Inc. All Rights Reserved. Quotient, the Coupons.com logo and the Quotient logo are trademarks of Quotient Technology Inc. All other trademarks,

More information

Case Studies On Data Mining In Market Analysis Shravan Kumar Manthri 1 and Hari Priyanka Chilakalapudi 2

Case Studies On Data Mining In Market Analysis Shravan Kumar Manthri 1 and Hari Priyanka Chilakalapudi 2 Case Studies On Data Mining In Market Analysis Shravan Kumar Manthri 1 and Hari Priyanka Chilakalapudi 2 Abstract- A huge chunk of data is generated each minute in enterprise business. Extracting information

More information

Daily Operations Guide

Daily Operations Guide Daily Operations Guide Detailed Overview of The Reports in The Envision Software I Day-to-Day Operations Guide Table of Contents Part I Welcome to Envision Cloud 1 Part II Daily Operations 2 1 Clocking

More information

Contoh Pengembangan SIM

Contoh Pengembangan SIM Contoh Pengembangan SIM Project Management Project Management Project Management Project Management Expectation Management Matrix Initial Expectation Adjusting Expectation Changing Priorities Problem

More information

Customer Loyalty Optimization

Customer Loyalty Optimization Organizational Intelligence Forum June 16-17 Boston, MA Customer Loyalty Optimization Executing customer loyalty and relationship management with a sound insights and data strategy JPK Group June 16, 2:15pm

More information

WEEK 9 DATA MINING 1

WEEK 9 DATA MINING 1 WEEK 9 DATA MINING 1 Week 9 Data Mining Introduction The purpose of this paper is to present the illustration of different aspects, which are associated with data mining. In the current era, businesses

More information

FOR MORE PAPERS LOGON TO

FOR MORE PAPERS LOGON TO MGT301 - Principles of Marketing When Olympia Carpets develops new carpets that are highly stain resistant and durable, it must educate consumers about the product's benefits. This activity calls for which

More information

MIDTERM #1 VERSION 1

MIDTERM #1 VERSION 1 Econ 101 Lec 3 Fall 2001 Midterm #1 Version 1 October 2, 2001 Student Name: ID Number: Section Number: TA Name: MIDTERM #1 VERSION 1 DO NOT BEGIN WORKING UNTIL THE INSTRUCTOR TELLS YOU TO DO SO. READ THESE

More information

3.2. Cases Segmentation, clustering

3.2. Cases Segmentation, clustering 3 Cases 3.2 3.2.1 Segmentation, clustering Introduction Segmentation is often defined as being able to discern a group of entities with common characteristics. From a mass of data one or more useful groups

More information

Chapter 10 - Direct Marketing and Sales Promotion

Chapter 10 - Direct Marketing and Sales Promotion Chapter 10 - Direct Marketing and Sales Promotion Direct Marketing is the process by which organizations communicate directly with target customers to generate a response or transaction. Direct marketing

More information

Sequential market basket analysis

Sequential market basket analysis Mark Lett (2012) 23:505 516 DOI 10.1007/s11002-012-9181-6 Sequential market basket analysis Wagner A. Kamakura Published online: 22 May 2012 # Springer Science+Business Media, LLC 2012 Abstract Market

More information

Consumer Mobile Shopper Solution

Consumer Mobile Shopper Solution Consumer Mobile Shopper Solution According to a recent retail study, more than fifty percent of shoppers surveyed say they want to use a mobile device while shopping, and to do final checkout at a self-checkout

More information

PCH Loyalty Reward Perks Reference Manual Finestra POS Version: 6.8.5

PCH Loyalty Reward Perks Reference Manual Finestra POS Version: 6.8.5 PCH Loyalty Reward Perks Reference Manual Finestra POS Version: 6.8.5 Please contact POSitec Customer Support regarding Customer Support, Training and all POS related issues. POSitec Customer Support:

More information

Economics 101 Midterm Exam #1. October 4, Instructions

Economics 101 Midterm Exam #1. October 4, Instructions Economics 101 Midterm Exam #1 October 4, 2001 Instructions Do not open the exam until you are instructed to begin. You will need a #2 lead pencil. If you do not have one you will need to borrow one from

More information

Sequential Association Rules Based on Apriori Algorithm Applied in Personal Recommendation

Sequential Association Rules Based on Apriori Algorithm Applied in Personal Recommendation , pp.257-264 http://dx.doi.org/10.14257/ijdta.2016.9.6.26 Sequential Association Rules Based on Apriori Algorithm Applied in Personal Recommendation Wang Yonggang School of information science and technology,

More information

> Low. margins. above. Retailers CONTROL. needs of single. and stock CONTROL. this brochure: - Sales processing. - Loyalty Programs - Visual cards

> Low. margins. above. Retailers CONTROL. needs of single. and stock CONTROL. this brochure: - Sales processing. - Loyalty Programs - Visual cards Supermarket and Grocery Retailers INTRODUCTION Industry Challenges > Increased competition acrosss independents and largerr supermarkets > Low margins > Dealing with complexities: (i. e. perishable products;

More information

Closing the Omni-channel Loop. via Dynamic, Data Driven Mobile Coupons

Closing the Omni-channel Loop. via Dynamic, Data Driven Mobile Coupons Closing the Omni-channel Loop via Dynamic, Data Driven Mobile Coupons Results SwiftIQ Platforms Commerce Analytics / Category Captain Merchandising Marketing Attribution Sales / Supply Chain Personalization

More information

Marketing Analysis Toolkit: Customer Lifetime Value Analysis

Marketing Analysis Toolkit: Customer Lifetime Value Analysis 9-511-029 REV: JANUARY 18, 2017 THOMAS STEENBURGH JILL AVERY Marketing Analysis Toolkit: Customer Lifetime Value Analysis Introduction Customers are increasingly being viewed as assets that bring value

More information

Tutorial: Advanced Rule Modeling in Corticon Studio

Tutorial: Advanced Rule Modeling in Corticon Studio Tutorial: Advanced Rule Modeling in Corticon Studio Product Version: Corticon 5.5 Tutorial: Advanced Rule Modeling in Corticon Studio 1 Table of Contents Introduction... 4 The business problem... 5 Discovering

More information

Teacher's Guide. Lesson Four. Shopping Wisely 04/09

Teacher's Guide. Lesson Four. Shopping Wisely 04/09 Teacher's Guide $ Lesson Four Shopping Wisely 04/09 shopping wisely websites websites for shopping wisely The internet is probably the most extensive and dynamic source of information in our society. The

More information

The Correlation Between Distance Travelled And Spending

The Correlation Between Distance Travelled And Spending The Correlation Between Distance Travelled And Spending AUTHORS: Remington Free, Raphael Goldman-Pham, Maxim Vorobyov, and Devin Vyas SCHOOL: The Abelard School 10.17975/sfj-2015-002 Abstract: The research

More information

Chapter 17. promotional concepts and strategies. Section 17.1 The Promotional Mix. Section 17.2 Types of Promotion

Chapter 17. promotional concepts and strategies. Section 17.1 The Promotional Mix. Section 17.2 Types of Promotion Chapter 17 promotional concepts and strategies Section 17.1 Section 17.2 Types of Promotion Section 17.1 IMAGINE What might happen if business did not promote their products? Section 17.1 Explain the role

More information

CHAPTER 8 T Tests. A number of t tests are available, including: The One-Sample T Test The Paired-Samples Test The Independent-Samples T Test

CHAPTER 8 T Tests. A number of t tests are available, including: The One-Sample T Test The Paired-Samples Test The Independent-Samples T Test CHAPTER 8 T Tests A number of t tests are available, including: The One-Sample T Test The Paired-Samples Test The Independent-Samples T Test 8.1. One-Sample T Test The One-Sample T Test procedure: Tests

More information

Compliance at the Point of Sale

Compliance at the Point of Sale Compliance at the Point of Sale Presented by CJ Wolf MD, CHC, CPC, COC, CCEP Healthicity Senior Compliance Executive cj.wolf@healthicity.com Darryl Rhames CFE, CICA University Health System Dir. Compliance

More information

CHAPTER THREE DEMAND AND SUPPLY

CHAPTER THREE DEMAND AND SUPPLY CHAPTER THREE DEMAND AND SUPPLY This chapter presents a brief review of demand and supply analysis. The materials covered in this chapter provide the essential background for most of the managerial economic

More information

The Essential Questions You MUST Ask BEFORE You Choose A Payment Solution

The Essential Questions You MUST Ask BEFORE You Choose A Payment Solution If you own a company that receives payments from clients/customers, and/or pays out commissions or payrolls, you will know that finding a suitable payment solution is critical to minimize fraud, reduce

More information

and convenience stores

and convenience stores RETAIL MANAGEMENT SOFTWARE SYSTEMS for supermarkets, grocery and convenience stores From gourmet food stores to multi-department supermarkets and everything in between the LS Retail solutions help you

More information

CHAPTER 5: DISCRETE PROBABILITY DISTRIBUTIONS

CHAPTER 5: DISCRETE PROBABILITY DISTRIBUTIONS Discrete Probability Distributions 5-1 CHAPTER 5: DISCRETE PROBABILITY DISTRIBUTIONS 1. Thirty-six of the staff of 80 teachers at a local intermediate school are certified in Cardio- Pulmonary Resuscitation

More information

Listening to The Voice of The Customer 1

Listening to The Voice of The Customer 1 Listening to The Voice of The Customer 1 To ensure that products and services satisfy customer needs, it is essential for a firm to gather their customers voice. Stated differently, listening to customers

More information

Foodstuffs Coupon Code of Practice

Foodstuffs Coupon Code of Practice Foodstuffs Coupon Code of Practice For the purpose of this Code, the term Foodstuffs refers to the wider Foodstuffs organisation including all Foodstuffs companies and all their respective member stores.

More information

What is Necessary for a Successful Supply Chain

What is Necessary for a Successful Supply Chain What is Necessary for a Successful Supply Chain Ron Klimberg Decision & System Sciences Haub School of Business Saint Joseph s University Philadelphia, PA USA Collaboration Trust Beer Game Orders Delay

More information

OfferArchitect The new paradigm for digital offer testing

OfferArchitect The new paradigm for digital offer testing OfferArchitect The new paradigm for digital offer testing 2016 RevTrax. All rights reserved. Products and services described herein are the proprietary and patent pending property of RevTrax. sales@revtrax.com

More information

Business Data Analytics

Business Data Analytics MTAT.03.319 Business Data Analytics Lecture 1: Introduction Marlon Dumas and Anna Leontjeva FirstName. LastName @ ut.ee Your background Your expectations Warm-up question We are a charity. We have a database

More information

Measuring Results of Your Loyalty Program Investment

Measuring Results of Your Loyalty Program Investment Remember Department Store pioneer John Wanamaker s famous quotation, I know I waste half the money I spend on advertising The problem is I don t know which half. One of the problems with advertising is

More information

arguments for and against and explain which you believe is soundest based on your understanding.

arguments for and against and explain which you believe is soundest based on your understanding. 1. Should the federal government continue to provide Amtrak with subsides? Provide economic arguments for and against and explain which you believe is soundest based on your understanding. 2. Based on

More information

Integrating Market and Credit Risk Measures using SAS Risk Dimensions software

Integrating Market and Credit Risk Measures using SAS Risk Dimensions software Integrating Market and Credit Risk Measures using SAS Risk Dimensions software Sam Harris, SAS Institute Inc., Cary, NC Abstract Measures of market risk project the possible loss in value of a portfolio

More information

6. In the early part of 1998, crude oil prices fell to a nine-year low at $13.28 a barrel.

6. In the early part of 1998, crude oil prices fell to a nine-year low at $13.28 a barrel. Questions 1. Delta Software earned $10 million this year. Suppose the growth rate of Delta's profits and the interest rate are both constant and Delta will be in business forever. Determine the value of

More information

Case Study Gauging the Impact of Display and Brand Messaging on the Cereal Category

Case Study Gauging the Impact of Display and Brand Messaging on the Cereal Category Case Study Gauging the Impact of Display and Brand Messaging on the Cereal Category in-store behavior monitoring system Disclaimer: This test was conducted by CART (Center For Advance Retail Technology),

More information

LECTURE 8 BY MAMURJON RAHIMOV UNESCO\UNITWIN OCW/OER UUOOI.ORG WIUT.UZ. Sales Promotion and Direct Marketing

LECTURE 8 BY MAMURJON RAHIMOV UNESCO\UNITWIN OCW/OER UUOOI.ORG WIUT.UZ. Sales Promotion and Direct Marketing LECTURE 8 BY MAMURJON RAHIMOV UNESCO\UNITWIN OCW/OER UUOOI.ORG WIUT.UZ Sales Promotion and Direct Marketing 'YOU CAN LEAD A HORSE TO WATER, BUT YOU CAN'T MAKE IT DRINK' Advertising brings the horse to

More information

pm4dev, 2016 management for development series Project Scope Management PROJECT MANAGEMENT FOR DEVELOPMENT ORGANIZATIONS

pm4dev, 2016 management for development series Project Scope Management PROJECT MANAGEMENT FOR DEVELOPMENT ORGANIZATIONS pm4dev, 2016 management for development series Project Scope Management PROJECT MANAGEMENT FOR DEVELOPMENT ORGANIZATIONS PROJECT MANAGEMENT FOR DEVELOPMENT ORGANIZATIONS A methodology to manage development

More information

The Coca Cola Branding And Packaging Marketing Essay

The Coca Cola Branding And Packaging Marketing Essay The Coca Cola Branding And Packaging Marketing Essay ukessays.com /essays/marketing/the-coca-cola-branding-and-packaging-marketing-essay.php Present customer encouragement strategies may differ to a great

More information

IM S5028. Architecture for Analytical CRM. Architecture for Analytical CRM. Customer Analytics. Data Mining for CRM: an overview.

IM S5028. Architecture for Analytical CRM. Architecture for Analytical CRM. Customer Analytics. Data Mining for CRM: an overview. Customer Analytics Data Mining for CRM: an overview Architecture for Analytical CRM customer contact points Retrospective analysis tools OLAP Query Reporting Customer Data Warehouse Operational systems

More information

Category Management Needs New Life

Category Management Needs New Life WINSTON WEBER & ASSOCIATES, INC. Global Leading Edge Thinking Practical Application Category Management Needs New Life * * * Category Management, as currently defined, is no longer adding incremental value

More information

Customer Satisfaction Survey Report Guide

Customer Satisfaction Survey Report Guide OVERVIEW The survey is designed to obtain valuable feedback and assess customer satisfaction among departments at CSU San Marcos. The survey consists of ten standard items measured on a 5-point scale ranging

More information

Midterm 2 - Solutions

Midterm 2 - Solutions Ecn 100 - Intermediate Microeconomic Theory University of California - Davis November 13, 2009 Instructor: John Parman Midterm 2 - Solutions You have until 11:50am to complete this exam. Be certain to

More information

Indicate whether the sentence or statement is True or False. Mark "A" if the statement is True or "B" if it is False.

Indicate whether the sentence or statement is True or False. Mark A if the statement is True or B if it is False. 2004 SLC Economics Page 1 Indicate whether the sentence or statement is True or False. Mark "A" if the statement is True or "B" if it is False. 1. The marginal social cost equals the marginal private cost

More information

Chapter 21. channels of distribution. Section 21.1 Distribution. Section 21.2 Distribution Planning

Chapter 21. channels of distribution. Section 21.1 Distribution. Section 21.2 Distribution Planning Chapter 21 channels of distribution Section 21.1 Section 21.2 Planning REFLECT How do bananas reach your local grocery store? Explain the concept of channel of distribution. Identify channel members. Compare

More information

Ahold Delhaize. Capital. Markets. Day 2018

Ahold Delhaize. Capital. Markets. Day 2018 Ahold Delhaize Capital Markets Day 2018 Kevin Holt Chief Executive Officer 2 Video Across all brands, is the leader on the East Coast ~2,000 stores across all brands ~30 years as online grocery leader

More information

Participant Handbook. Retail Cashier. Sector. Sub-Sector Retail Operations. Reference ID: RAS/Q0102, Version 1.0 NSQF: Level 2

Participant Handbook. Retail Cashier. Sector. Sub-Sector Retail Operations. Reference ID: RAS/Q0102, Version 1.0 NSQF: Level 2 Participant Handbook Sector 9 7 8-8 1-8 3 2 3-1 6 4-0 Sub-Sector Retail Operations Reference ID: RAS/Q0102, Version 1.0 NSQF: Level 2 Housekeeping A endant Retail Cashier Published by EXCEL BOOKS PRIVATE

More information

SaaS Retail Software & ecommerce ONE SYSTEM. TOTAL RETAIL.

SaaS Retail Software & ecommerce ONE SYSTEM. TOTAL RETAIL. SaaS Retail Software & ecommerce ONE SYSTEM. TOTAL RETAIL. Cloud SaaS Retail Software MANAGE YOUR ENTIRE RETAIL BUSINESS WITH ONE SYSTEM With so many Cloud-based, SaaS options in the retail software market,

More information