Sign up FAST! Login

Data Science Use Cases

lisa simpson computer

BackgroundFor each type of analysis think about:

  • What problem does it solve, and for whom?
  • How is it being solved today?
  • How can it beneficially affect business?
  • What are the data inputs and where do they come from?
  • What are the outputs and how are they consumed- (online algorithm, a static report, etc)
  • Is this a revenue leakage ("saves us money") or a revenue growth ("makes us money") problem?

Use Cases By FunctionMarketingPredicting Lifetime Value (LTV)

  • what for: if you can predict the characteristics of high LTV customers, this supports customer segmentation, identifies upsell opportunties and supports other marketing initiatives
  • usage: can be both an online algorithm and a static report showing the characteristics of high LTV customers
Wallet share estimationworking out the proportion of a customer's spend in a category accrues to a company allows that company to identify upsell and cross-sell opportunitiesusage: can be both an online algorithm and a static report showing the characteristics of low wallet share customers Churnworking out the characteristics of churners allows a company to product adjustments and an online algorithm allows them to reach out to churnersusage: can be both an online algorithm and a statistic report showing the characteristics of likely churners Customer segmentationIf you can understand qualitatively different customer groups, then we can give them different treatments (perhaps even by different groups in the company). Answers questions like: what makes people buy, stop buying etcusage: static report Product mixWhat mix of products offers the lowest churn? eg. Giving a combined policy discount for home + auto = low churnusage: online algorithm and static report Cross selling/Recommendation algorithms/Given a customer's past browsing history, purchase history and other characteristics, what are they likely to want to purchase in the future?usage: online algorithm Up sellingGiven a customer's characteristics, what is the likelihood that they'll upgrade in the future?usage: online algorithm and static report Channel optimizationwhat is the optimal way to reach a customer with certain characteristics?usage: online algorithm and static report Discount targetingWhat is the probability of inducing the desired behavior with a discountusage: online algorithm and static report Reactivation likelihoodWhat is the reactivation likelihood for a given customerusage: online algorithm and static report Adwords optimization and ad buyingcalculating the right price for different keywords/ad slots

SalesLead prioritization

  • What is a given lead's likelihood of closing
  • revenue impact: supports growth
  • usage: online algorithm and static report
Demand forecasting

LogisticsDemand forecastingHow many of what thing do you need and where will we need them? (Enables lean inventory and prevents out of stock situations.)revenue impact: supports growth and militates against revenue leakageusage: online algorithm and static reportRiskCredit risk

Treasury or currency riskHow much capital do we need on hand to meet these requirements? Fraud detectionpredicting whether or not a transaction should be blocked because it involves some kind of fraud (eg credit card fraud) Accounts Payable RecoveryPredicting the probably a liability can be recovered given the characteristics of the borrower and the loan Anti-money launderingUsing machine learning and fuzzy matching to detect transactions that contradict AML legislation (such as the OFAC list)

Customer supportCall centers

  • Call routing (ie determining wait times) based on caller id history, time of day, call volumes, products owned, churn risk, LTV, etc.
Call center message optimizationPutting the right data on the operator's screen Call center volume forecastingpredicting call volume for the purposes of staff rostering

Human ResourcesResume screening

  • scores resumes based on the outcomes of past job interviews and hires
Employee churnpredicts which employees are most likely to leave Training recommendationrecommends specific training based of performance review data Talent managementlooking at objective measures of employee success

Use Cases By VerticalHealthcareClaims review prioritization

  • payers picking which claims should be reviewed by manual auditors
Medicare/medicaid fraudTackled at the claims processors, EDS is the biggest & uses proprietary tech Medical resources allocationHospital operations managementOptimize/predict operating theatre & bed occupancy based on initial patient visits Alerting and diagnostics from real-time patient dataEmbedded devices (productized algos)Exogenous data from devices to create diagnostic reports for doctors Prescription compliancePredicting who won't comply with their prescriptions Physician attritionHospitals want to retain Drs who have admitting privileges in multiple hospitals Survival analysisAnalyse survival statistics for different patient attributes (age, blood type, gender, etc) and treatments Medication (dosage) effectivenessAnalyse effects of admitting different types and dosage of medication for a disease Readmission riskPredict risk of re-admittance based on patient attributes, medical history, diagnose & treatment

Consumer FinancialCredit card fraudBanks need to prevent, and vendors need to preventRetail (FMCG - Fast-moving consumer goods)Pricing

  • Optimize per time period, per item, per store
  • Was dominated by Retek, but got purchased by Oracle in 2005. Now Oracle Retail.
  • JDA is also a player (supply chain software)
Location of new storesPioneerd by TescoDominated by BuxtonSite Selection in the Restaurant Industry is Widely Performed via Pitney Bowes AnySite Product layout in storesThis is called "plan-o-gramming" Merchandizingwhen to start stocking & discontinuing product lines Inventory Management (how many units)In particular, perishable goods Shrinkage analyticsTheft analytics/prevention ( Warranty AnalyticsRates of failure for different componentsAnd what are the drivers or parts?What types of customers buying what types of products are likely to actually redeem a warranty? Market Basket Analysis Cannibalization Analysis Next Best Offer Analysis In store traffic patterns (fairly virgin territory)

InsuranceClaims prediction

  • Might have telemetry data
Claims handling (accept/deny/audit), managing repairer network (auto body, doctors) Price sensitivity Investments Agent & branch performance DM, product mix

ConstructionContractor performance

  • Identifying contractors who are regularly involved in poor performing products
Design issue predictionPredicting that a construction project is likely to have issues as early as possible

Life SciencesIdentifying biomarkers for boxed warnings on marketed products

Drug/chemical discovery & analysis Crunching study results Identifying negative responses (monitor social networks for early problems with drugs) Diagnostic test developmentHardware devicesSoftware Diagnostic targeting (CRM) Predicting drug demand in different geographies for different products Predicting prescription adherence with different approaches to reminding patients Putative safety signals Social media marketing on competitors, patient perceptions, KOL feedback Image analysis or GCMS analysis in a high throughput manner Analysis of clinical outcomes to adapt clinical trial design COGS optimization Leveraging molecule database with metabolic stability data to elucidate new stable structures

Hospitality/ServiceInventory management/dynamic pricing

Promos/upgrades/offers Table management & reservations Workforce management (also applies to lots of verticals)

Electrical grid distributionKeep AC frequency as constant as possibleSeems like a very "online" algorithmManufacturingSensor data to look at failures

Quality managementIdentifying out-of-bounds manufacturingVisual inspection/computer visionOptimal run speeds Demand forecasting/inventory management Warranty/pricing

TravelAircraft scheduling

Seat mgmt, gate mgmt Air crew scheduling Dynamic pricing Customer complain resolution (give points in exchange) Call center stuff Maintenance optimization Tourism forecasting

AgricultureYield management (taking sensor data on soil quality - common in newer John Deere et al truck models and determining what seed varieties, seed spacing to use etcMall OperatorsPredicting tenants capacity to pay based on their sales figures, their industry

Predicting the best tenant for an open vacancy to maximise over all sales at a mall

EducationAutomated essay scoringUtilitiesOptimise Distribution Network Cost Effectiveness (balance Capital 7 Operating Expenditure)Predict Commodity RequirementsOtherSentiment analysis

Loyalty programs Sensor dataAlertingWhat's going to fail? De duplication Procurement

Use Cases That Need Fleshing OutProcurementNegotiation & vendor selectionAre we buying from the best producerMarketingDirect Marketing

  • Response rates
  • Segmentations for mailings
  • Reactivation likelihood
  • RFM
  • Discount targeting
  • FinServ
  • Phone marketing
    • Generally as a follow-up to a DM or a churn predictor
  • Email Marketing
OfflineCall to action w/ unique promotionWhy are people responding- How do I adjust my buy (where, when, how)?"I'm sure we are wasting half our money here, but the problem is we don't know which ad" Media Mix OptimizationKantar Group and Nielson are dominantHard part of this is getting to the data (good samples & response vars)

HealthcareCRM & utilization optimization

Claims coding Forumlary determination and pricing How do I get you to use my card for auto-pay? Paypal? etc. Unsolved. FinanceRisk analysisAutomating Excel stuff/summary reports

Stashed in:

To save this post, select a stash from drop-down menu or type in a new one:

You May Also Like: