Data Mining in Industry: Putting Theory into Practice Bhavani Raskutti.

Slides:



Advertisements
Similar presentations
Data Mining: What? WHY? HOW?
Advertisements

Partnership between research and industry for developing innovative data mining applications Bhavani Raskutti Analytic CRM Westpac.
Data Mining in Industry: Putting Theory into Practice Bhavani Raskutti.
Ensuring big data is supporting financial analytics Gaining a thorough understanding of big data in order to understand analytics Transforming unstructured.
Career Opportunities in Statistical Computing. Two Perspectives on Careers in Statistical Computing 1.Software development opportunities at SAS 2.Emerging.
Customer relationship management.
Customer relationship management.
Analytical Model Development & Implementation Experience from the Field Bhavani Raskutti.
Chapter 9 Business Intelligence Systems
April 28, 2015 Virginia Tech. Data Analytics “Analytics is the combustion engine of business, and it will be necessary for organizations that want to.
Decision Support Chapter 10. Overview Databases are really information technology Decision Support is a business application that actually uses databases.
Database – Part 2b Dr. V.T. Raja Oregon State University External References/Sources: Data Warehousing – Sakthi Angappamudali at Standard Insurance; BI.
Data Mining.
Business Intelligence Andrew Davis Andria Zippler Jana Krinsky Tiffany Ferris.
Chapter 14 The Second Component: The Database.
Enterprise Applications and Business Process Integration
Business Intelligence
The Strategic Role of Information in Sales Management
Customer relationship management systems Lecture 10.
DASHBOARDS Dashboard provides the managers with exactly the information they need in the correct format at the correct time. BI systems are the foundation.
Spreadsheet in excel o Spreadsheet in excel o Uses of spreadsheet o Advantages Prepared by: Yusra Waseem 8 th C.
Retail and Consumer Roadmap to Retailing in the Digital Era Strictly Private and Confidential 17 June 2015.
Data Mining By Andrie Suherman. Agenda Introduction Major Elements Steps/ Processes Tools used for data mining Advantages and Disadvantages.
Types of CRM Operational CRM – supports traditional transactional processing for day-to-day front-office operations or systems that deal directly.
Module 3: Business Information Systems Enterprise Systems.
Chapter 5: Data Mining for Business Intelligence
Shilpa Seth.  What is Data Mining What is Data Mining  Applications of Data Mining Applications of Data Mining  KDD Process KDD Process  Architecture.
Data Mining Techniques As Tools for Analysis of Customer Behavior
DATA MINING Team #1 Kristen Durst Mark Gillespie Banan Mandura University of DaytonMBA APR 09.
Global Pyrethroids Industry Development and Cost Analysis Report 2015
GBA IT Project Management Final Project – “ FoodMart Corp - Making use of Business Intelligence” July 12, 2004 N.Khuda.
DATA MINING Prof. Sin-Min Lee Surya Bhagvat CS 157B – Spring 2006.
Fox MIS Spring 2011 Data Mining Week 9 Introduction to Data Mining.
Data Mining: Software Helping Business Run
Chapter 5: Business Intelligence: Data Warehousing, Data Acquisition, Data Mining, Business Analytics, and Visualization DECISION SUPPORT SYSTEMS AND BUSINESS.
© 2010 IBM Corporation Business Analytics software Business Analytics Editable Text Editable Text Editable Text.
© 2012 Ideal Analytics Limited. Retail. © 2012 Ideal Analytics Limited. 2 Retail outlets – Producers of ever changing data  Retail business outlets transact.
Data Mining BY JEMINI ISLAM. Data Mining Outline: What is data mining? Why use data mining? How does data mining work The process of data mining Tools.
MIS2502: Data Analytics Advanced Analytics - Introduction.
Data Mining Copyright KEYSOFT Solutions.
PROPRIETARY  2003 Data Research Analysis & Consultancy Solutions All Rights Reserved. This is achieved by: Improving availability / reducing stock outs.
Impact Research 1 Enabling Decision Making Through Business Intelligence: Preview of Report.
D ATA S CIENTISTS Who are they and what do they do?
Global Rectifier Diode Industry Product, Trends, Growth Research Report 2015 Published: Sep 2015 Single User License: US$ 2800 Corporate User License:
Data Mining With SQL Server Data Tools Mining Data Using Tools You Already Have.
BUSINESS INTELLIGENCE. The new technology for understanding the past & predicting the future … BI is broad category of technologies that allows for gathering,
Introduction to Business Analytics
1 © 2014 by McGraw-Hill Education. This is proprietary material solely for authorized instructor use. Not authorized for sale or distribution in any manner.
Chapter 3 Building Business Intelligence Chapter 3 DATABASES AND DATA WAREHOUSES Building Business Intelligence 6/22/2016 1Management Information Systems.
Global Oil Pressure Sensor Industry Trends, Share and Competitive Landscape Research Report 2015 Published: Oct 2015 Single User License: US$ 2800 Corporate.
Proposal and Company Information Document CONTENT About Indagatio Research Our Research Offerings Why Indagatio Research Our Work Process Project Snapshot.
Predictive Analytics Market to Global Analysis and Forecasts by Applications, Business Function, Deployment Model No of Pages: 150 Publishing Date:
Predictive Analytics Market to Global Analysis and Forecasts by Applications, Business Function, Deployment Model No of Pages: 150 Publishing Date:
What we mean by Big Data and Advanced Analytics
01-Business intelligence
Data Mining.
Data Mining, Machine Learning, Data Analysis, etc. scikit-learn
Data Based Decision Making
Business Intelligence Big Data Jan 24, 2018
GLOBAL STREAMING ANALYTICS MARKET - SIZE, TREND, SHARE, OPPORTUNITY ANALYSIS & FORECAST,
כריית מידע -- מבוא ד"ר אבי רוזנפלד.
CUSTOMER RELATIONSHIP MANAGEMENT CONCEPTS AND TECHNOLOGIES
Data Science introduction.
Data Mining, Machine Learning, Data Analysis, etc. scikit-learn
Global And Regional Data Mining Tools Industry Production, Sales And Consumption Status And Prospects Professional Market Research Report David.
Data Mining, Machine Learning, Data Analysis, etc. scikit-learn
Welcome! Knowledge Discovery and Data Mining
Adroit Market Research +1 (214) Single Use License: US$ 4800 Request Sample Global.
Presentation transcript:

Data Mining in Industry: Putting Theory into Practice Bhavani Raskutti

Agenda What do analysts in industry actually do? Who are our customers & colleagues? What resources do we use? Who uses analytics in Australian Industry? Case studies Take-home Points

What do analysts in industry actually do? Business understanding of complex trends To make strategic & operational decisions Business Problem Data Acquisition & Preparation DAP Problem Definition PD D Deployment Presentation P Mathematical Modelling (Algorithms) Data Matrix MM Initial Development Iterative 90% DAP Decision-making by users Insights via GUI Automation Training Documentation IT Support

Who are our customers & colleagues? Customers of Analytics Marketing Design Sales Supply Chain Senior Management Analytics Data Mining Statistical analysis, machine learning Maths/Stats/Science graduates Market Research Behavioural analysis psych/mktg/SocSc graduates Business Intelligence Historical Reporting CS/IT graduates Business/ Corporate Information Technology

What resources do we use? Data Extraction – SQL: from databases such as Oracle, DB2, mySQL, … Exploratory/Visualisation – Tableau: Multi-dimensional visual analysis with ability to publish and connectivity to most databases Tableau – Qlikview: Very similar to Tableau, later entrant into Australia Qlikview – Excel: Great for exploration, although businesses use it as the only analysis tool Statistical Modelling Expensive commercial tools used in financial & telecommunications industry. – SAS: Industry leader with broad statistical service offering, but license is expensive SAS – KXEN: Recent entrant, but innovative with particular focus on large datasets & automation. KXEN – Salford systems: Well established leader with focus on regression trees and explainable models. Salford systems – SPSS, Statistica, Matlab: Niche players appealing to certain communities. SPSSStatisticaMatlab Open source or low priced data mining tools: – Weka is open source software issued under the GNU General Public License. Weka – RapidMiner is available under a dual license: GNU licence or a proprietary license. RapidMiner – R is a free software environment for statistical computing and graphics. Needs compilation. R Presentation – Cognos, Business Objects, Tableau, …

Who uses analytics in Australian industry? IndustryClustering / Segmentation Classification / Scoring Other Customer/market segmentation Survey analysis Sentiment analysis … Upsell/Cross-sell Fraud detection Credit scoring Location services Churn modelling … Marketing effectiveness Market share understanding Next best offer Asset management … Telecom Finance Wholesale Retail Bio-informatics Government, Utilities, Pharmaceuticals, Manufacturing, Web service providers Consulting firms, Data mining vendors

IndustryClustering / Segmentation Classification / Scoring Other Customer/market segmentation Survey analysis Sentiment analysis … Upsell/Cross-sell Fraud detection Credit scoring Location services Churn modelling … Marketing effectiveness Market share understanding Next best offer Asset management … Telecom Finance Wholesale Retail Bio-informatics Government, Utilities, Pharmaceuticals, Manufacturing, Web service providers, … Consulting firms, Data mining vendors, Market research firms, … Who uses analytics in Australian industry?

DAP PD D P MM - Sales  demand - Similar similar outlets have similar demand to sales relationship - Anomaly may be due to lack of stock Case Study: Wholesale Industry Increase wholesale sales into major retailers - Quantify demand - Define normalised sell-rate - Define a long term in-stock measure - Define products & outlets that are similar - Weekly SOH & sales for each store & SKU - SKU master - Store master Simple univariate regression in SQL Perform comparisons & find anomalies with stock issues - Self-serve report in Cognos for each sales rep - Presents list of products with opportunities - Opportunities click through to detailed graphs showing demand, sales & stock position of the two products compared

Demand In-stock % ·R1 ·R2 Demand Sell Rate Case Study: Wholesale Industry (Cont’d)

DAP PD D P MM - Sales  demand - Similar similar outlets have similar demand to sales relationship - Anomaly may be due to lack of stock Increase wholesale sales into major retailers - Quantify demand - Define normalised sell-rate - Define a long term in-stock measure - Define products & outlets that are similar - Weekly SOH & sales for each store & SKU - SKU master - Store master Simple univariate regression in SQL - Self-serve report in Cognos for each sales rep - Presents list of products with opportunities - Opportunities click through to detailed graphs showing demand, sales & stock position of the two products compared - Implementation in SQL & Cognos - DataMarts for reports updated weekly - Documentation on intranet wiki - Training by corporate training team - Support from IT helpdesk Perform comparisons & find anomalies with stock issues Case Study: Wholesale Industry (Cont’d)

Agenda What do analysts in industry actually do? Who are our customers & colleagues? What resources do we use? Who uses analytics in Australian Industry Who uses analytics in Australian Industry Case studies Take-home Points

Win-back? Stop churn? Upsell? DAP PD D P MM - Winning back customers is hard - Churn is hard to identify and harder to prevent - Upsell to existing customers increases retention & revenue Increase revenue from business customers Imbalanced data – too few examples of take-up for most products - Data aggregation & Interleaving Comparable predictors from revenue - Raw, change from previous, projected - Use values as is & normalised - Binarise using 10 equi-size bins - Satisfaction survey - Service assurance - Demographics - Quarterly revenue from different products for each customer - SVMs to score with likelihood of take-up - Weighting by value of take-up to find high value take-up Excel spread sheet with potential customer list - Take-up likelihood for all modelled products - Last quarter revenue for all products - Implementation in Matlab & C - Different predictive models for over 50 products in 4 segments - Automatic updates every quarter - Used by sales consultants to re- negotiate contracts Create models to predict customers likely to take up a product soon i-5 i-4 i-3 i-2 i-4 i-3 i-2 i-1 i-3 i-2 i-1 i i-1 i i+1 i+2 Predictors Prediction Labels TRAINTRAIN Case Study: Telecommunications Industry

Evaluation: Piloted predictive modelling in 2 different regions – Region 1: 9 new opportunities from just 5 products with an increase in revenue of ~400K A$ – Region 2: Opportunities identified were already being processed by sales consultants Conclusion: Predictive modelling better than previous manual process – Identifies more opportunities – Spreads techniques of good sales teams across the whole organisation Deployed in 2004 & still operational For more details, refer to “Predicting Product Purchase Patterns for Corporate Customers” by Bhavani Raskutti & Alan Herschtal in Proceedings of KDD’05, Chicago, Illinois, USA Case Study: Telecommunications Industry (Cont’d)

Take-home points Data acquisition & processing phase forms 80-90% of any analytics project Business users are tool agnostic – R, SAS, Matlab, SPSS, … for statistical analysis – Tableau, Cognos, Excel, VB, … for presentation Business adoption of analytics driven by – Utility of application – Ease of decision-making from insights – Ability to explain insights

Questions?