An Introduction to Advanced analytics and data mining

An Introduction to Advanced analytics and data mining

• 1.
  An Introduction to AdvancedAnalytics and Data Mining Transforming Data Dr Barry Leventhal April 2014 © Copyright BarryAnalytics Limited All Rights Reserved
• 2.
  Agenda • What areAdvanced Analytics and Data Mining? • The toolkit of data mining techniques • Some issues to keep in mind Transforming Data • Which technique should you use?
• 3.
  A process ofdiscovering and interpreting patterns in (often large) data sets in order to solve business problems What is Data Mining? Transforming Data Converts Data into Information Pattern Information ActionData
• 4.
  What is AdvancedAnalytics? “Any solution that supports the identification of meaningful patterns and correlations among variables in complex, structured and unstructured, historical, and potential future data sets for the purposes of predicting future events and assessing the Data Visualisation Web Analytics Text Analysis Transforming Data purposes of predicting future events and assessing the attractiveness of various courses of action. Advanced Analytics typically incorporate such functionality as data mining, descriptive modelling, econometrics, forecasting, operations research optimisation, predictive modelling, simulations, statistics and text analytics.” (Source: Forrester Research) Data Mining Contact Optimisation Simulation Social Network Analysis
• 5.
  How can AdvancedAnalytics help? • By helping companies to increase revenues or reduce costs increase revenues reduce costs Transforming Data improve profit Tom Davenport: “Companies have long used business intelligence for specific applications, but these initiatives were too narrow to affect corporate performance. Now, leading firms are basing their competitive strategies on the sophisticated analysis of business data.”
• 6.
  Where can AdvancedAnalytics add Value? Store location Product management Customer Transportation /Fleet management Resource planning Transforming Data Customer management Web site management Anywhere else where I have large numbers to manage planning
• 7.
  The Toolkit ofData Mining Techniques Transforming Data Traditional Statistics • Regression Models • Survival Analysis • Factor Analysis • Cluster Analysis • CHAID Machine Learning • Rule Induction • Neural Networks • Genetic Algorithms
• 8.
  Two main typesof Analytical Model Type 1: Models driven by a Target Variable e.g. Which customers to cross sell? - Implies building a Predictive Model - ‘Directed’ Data Mining Techniques Transforming Data - ‘Directed’ Data Mining Techniques Type 2: Models with no Target Variable e.g. What are our most important customer segments? - Implies a Descriptive Model - ‘Undirected’ Data Mining Techniques
• 9.
  The Data MiningProcess Transforming Data Data Cross Industry Standard Process for Data Mining Reference: Step-by-step data mining guide CRISP-DM 1.0
• 10.
  Some issues tokeep in mind: Issue 1: Use an appropriate technique • Some years ago, the DMA Targeting & Statistics Group held a seminar to explain and compare four analytical techniques: – Cluster Analysis – Decision Tree – Neural Network (supervised) Transforming Data – Neural Network (supervised) – Regression Model • The four techniques were applied to a sample of lifestyle data in order to predict private healthcare cover
• 11.
  Comparison of privatehealthcare targeting via four analytical techniques 300 350 400 Some issues to keep in mind: Issue 1: Use an appropriate technique Transforming Data 100 150 200 250 10% 20% 30% 40% 50% Cluster Analysis Decision Tree Regression Model Neural Net Source: CMT/ DMA Targeting & Statistics Interest Group
• 12.
  Issue 2: Modellingand Deploying are separate stages in the data mining process Historical Data + Known Outcomes Modelling Model Deploying Transforming Data • “Modelling” is ‘one-off’ – until model requires rebuild • “Deploying” takes place repeatedly Recent Data + Deploying Model Predictions
• 13.
  Issue 3: Donot forget your data! Your data is the key to gaining value from analytics and modelling – essentials to consider: • Data quality Transforming Data • Data predictivity • Data integration • Data governance
• 14.
  The Importance ofData Integration Customer Transactions Customer Attributes Integration • Business value increased by integrating complementary datasets • New insights may be created by data integration, e.g. Transforming Data Market Research Online Behaviour Integration Many applications of data integration... • Predictive models to target behaviours identified by research • Integration of web, email and traditional offline channels • Tracking across channels, e.g. Attribution of media effects
• 15.
  Which analytical techniqueshould you use ? The choice generally depends on… • business problem • whether problem is predictive or descriptive • underlying data environment • variables to be predicted or described Transforming Data • variables to be predicted or described • ability to implement solution • whether key statistical assumptions hold • Obtain help from a Statistician or Data Mining Consultant • All about the problem, not the technique • Combination of approaches works best
• 16.
  Thank you! Barry Leventhal TransformingData +44 (0)7803 231870 [email protected]