4 Lifting the Mist What is the question? No exact answers? Assumptions? Variation (the same inputs don’t always give us the same answers)Vast amounts data.Is it clean?How do we present our inferences?
5 What is an analyst? Leads the data analysis/ Data capture Interprets the needs of the organisationUnderstands the data and the analysisCan speak a common language
6 Analytics VS Gut 40% of decisions are made on gut instinct. Statistical predictions consistently out perform gutExtensive evidence that having experts is good but experts using analysis is much betterExpert intuition is better only when there is no data and little time to get the data.
7 Problem solving with Analytics + Cigna health insuranceUsing phone calls to reduce the amount of time in hospital of its clientsUsed analytics to determine which illness had reduced time in hospital through phone call interventionSaved money by focusing staff on the right strategy with regard to phone calls
8 Problem solving with Analytics - AIGDidn’t listen to the quants with regard to the risks the company were taking with over leveraged CDSCost AIG billions and effectively put the planet into a tail spin.
9 History of AnalyticsAnalytics – ‘always’ been around (since 5000BC) - tablets found recording the amount of beer workers were consuming.WW2 – Focus on supply chain and target optimisation. Advent of Operations ResearchUPS created a ‘statistical analysis group’ in 195470’s: Intel employ statisticians to develop line optimisationHoward Dresner at Gartner defines “business intelligence”2010: Analytics begins to blend with decision management
10 Improvements? Faster computers Ability to store vast amounts of data. Processing powerAbility to store vast amounts of data.Cloud, hadoopBetter visual analyticsDashboardsGraphicsMore user friendly solutions (Excel, SAS, Cognos etc)
11 Problems Academic Vs Real World The interpretation is not always easy to understand or communicateThe world requires data faster and wants real time solutions,Mathematical Modelling is not intellectually easy.There is so much dataWhich data do we use?Structured vs non-structured data.Are our assumptions right?
12 Culture People not Knowing what they want Quants not been given a clear mandate by the organisationRapid change in operational and delivery technologiesLack of standards.
13 What’s needed? Data Enterprise Leadership Targets Communication ‘Quality’ , clean dataEnterpriseManagement approach/systems/softwareLeadershipPassion and commitmentTargetsGet the right Key Performance Indicators/metricsRemember, what gets measured gets managedCommunicationTraining/visuals
14 Leadership Training Professionalism Define metrics/KPI Ask the right questionPick the right projectsEngage management and get their commitmentShow the benefitsMake the results clear
15 Looking Outside the box What are other industries doing today that we could do tomorrowPharma randomised testsRetail/online price optimisationManufacturing real time yield reportingSystemsWhat do we have and can we get data from it?Is our data on different platforms ?Can we merge our data?Can we interrogate our data in an intelligent and efficient manner?
16 Quantitative Analysis 3 stages-6 steps: T. Davenport 1. Problem recognition2. Review of previous findingsStage 23. Modelling4. Data Collection5. Data AnalysisStage 36. Results presentation
17 Frame the Problem1. Problem Recognition – Usually starts with broad hypothesis – “We are spending to much money on market research”2. Review previous findings – Research the area. What are others doing?
18 Solve the problem 3. Modelling/ Variable selection 4. Data Collection. Precision/ measurement capabilityQualitative/ QuantitativeStructured/unstructured5. Data analysisTypes of stories-descriptive vs Inferential analysis
19 Results 6. Results Presentation and Action Academic not equal to ‘Normal’ InterpretationA Picture Tells a thousand Words
20 Communicating and Acting on Results Results presentation and actionNot normally focused on by academics. But beginning to change. Need to tell the story with narrative and pictures.
21 Examples of Success & failure Engineer wants to change printers on board manufacturing because boards are being sent wrong way on the line.Stopped them spending a fortune on replacing printers world wide.Line installation stopped from going wrong.Line approval was stopped until machine gave stable results.Pharmaceutical industry clinical trial on cancer patients and their reaction/adverse events to a drug.Obsession with significance testing
22 Types of analytical stories CSI Solve a problemSolve a long term problem with analyticsMAD Scientist – conducting experimentsSurvey the situationPrediction – use past results to tell the futureWhat happened –Straight forward reporting, descriptive statistics (accounts, CSO)
23 Measurement Problems Choice of measurement device critical Weigh up the ROI of the options and the results that can be got from it.27k simple single measurement device versus 350k for XRAY machine for measuring fat on Pigs.What are using the data for?Stability/Accuracy/Consistency and interpretation of Measurement is critical.Wrong measurement gives wrong conclusionsHow does one translate language into numbers?
24 What non-Quants (Deciders) should expect of Quants Learn the business process and problemCommunicate results in business termsSeek the truth with no predefined agenda.Help frame and communicate the problem, not just solve itDon’t wait to be asked
25 What Quants should expect of Non-Quants (Deciders) Form a relationship with your quant (Don’t lock them in a room)Give access to the business process and problemFocus primarily on framing the problem not solving itAsk lots of questions, especially on assumptions.Ask for help with the whole process
26 The future? Machine Learning Voice, Video, text Personalised Analysis i.e. what is *this particular* consumer likely to buy at this point in time when presented with these particular choicesAutomotive ModellingThe models adapt themselves to update analysis
27 It takes timeBuilding the capability takes a huge amount of time and resourcesBarclays 5 year plan on ”Information – based customer management”The big companies believe in it.Communication & Culture is key to success.Every organisation has vast amounts of data they are not using.
28 Mistakes Assumptions about the data? Failures to adapt models Proctor and Gamble run 5000 models a dayWrong interpretation of the models
29 Conclusion Follow the 6 steps Always question the data Where did they come fromHow were they measured?Are the data stable?Examine outliers/unusual eventsUnderstanding the problem always takes away the mist.Communication is key to success.Organisation needs a Culture/ Leadership to succeed in analytics.