Data Science Business Applications

by Chee Yee Lim

Posted on 2021-03-27

Collection of notes on data science business applications - a selection of business applications of data science across domains/industries

Applications By Business Functions


  • Customer segmentation
    • If 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 etc.
  • Predicting lifetime value (LTV)
    • If you can predict the characteristics of high LTV customers, this supports customer segmentation, identifies upsell opportunities and supports other marketing initiatives.
  • Wallet share estimation (i.e. customer spending pattern)
    • Working out the proportion of a customer's spend in a category accrues to a company allows that company to identify upsell and cross-sell opportunities.
  • 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?
  • Up selling
    • Given a customer's characteristics, what is the likelihood that the will upgrade in the future?
  • Channel optimisation
    • What is the optimal way to reach a customer with certain characteristics?
  • Churn
    • Working out the characteristics of churners allows a company to adjust products and an online algorithm allows them to reach out to churners.
  • Product mix
    • What mix of products offers the lowest churn? E.g. giving a combined policy discount for home + auto = low churn.
  • Discount targeting
    • What is the probability of inducing the desired behaviour with a discount?
  • Renewal / reactivation likelihood
    • What is the renewal / reactivation likelihood for a given customer?
  • Adwords optimisation and ad buying
    • Calculating the right price for different keywords/ad slots.
  • Lead prioritisation
    • What is a given lead's likelihood of closing the deal?
  • Demand forecasting
    • What is the future demand for specific products? From specific customer groups?
  • Media mix optimisation
    • How to most effectively market across different media (e.g. TV, social media)?


  • Negotiation & vendor selection
    • Are we buying from the best supplier?
    • Can we filter and select supplier based on internal criteria or strategy?
  • Risk management
    • (Suppliers) Can we manage and reduce risk from suppliers? In terms of financial, governance or sustainability.
    • (Transactions) Can we monitor and flag high risk transactions?


  • Route optimisation
    • This is a combinatorial optimisation problem, in the form of travelling salesman or vehicle routing problems.
    • Can be solved by using solvers for constraint programming, SAT solver etc.
  • Demand forecasting
    • Anticipate the demand changes from customer/market due to changes in internal (e.g. previous sales pattern) and/or external (e.g. macroeconomic) factors.
    • To enable lean inventory and prevents out of stock situations.
    • How many of each item do you need? When and where will we need them?
  • Risk management
    • Predict probability of disruptions on trade lanes due to congestions or natural disasters.

Financial Risk

  • Fraud detection
    • Predicting whether a transaction should be blocked because it involves some kind of frauds (e.g. credit card fraud).
  • Anti-money laundering (AML)
    • Using machine learning and fuzzy matching to detect transactions that contradict AML legislation.
  • Credit risk
    • What is the probability of a customer defaulting on his/her loan?
  • Accounts payable recovery
    • Predicting the probability a liability can be recovered given the characteristics of the borrower and the loan
  • Liquidity risk
    • How much capital do we need on hand to meet these requirements?

Customer Support

  • Income request routing
    • Routing based on customer history, handling capacity and other factors.
  • Handling efficiency
    • Improve efficiency (i.e. reduce handling time) by helping the operator to locate correct information quicker.
  • Volume forecasting
    • Predict incoming request volume for the purpose of staff rostering.
  • Customer satisfaction
    • Track and monitor the satisfaction of customers based on their interaction details and history.
  • Chat bot
    • Automate chats for simple requests by using chat bot.

Human Resources

  • Resume screening
    • Scores and filters resumes based on the outcomes of past job interviews and hires.
  • Employee churn
    • Predicts which employees are most likely to leave.
  • Training recommendation
    • Recommends specific training based on performance review data.
  • Talent management
    • Looks at objective measures of employee success.
  • Diversity management
    • Monitors and recommends ways to improve employee diversity (e.g. gender, ethnic).

Applications By Business Sectors


  • Medical resources allocation
    • Hospital operations management.
    • Optimise/predict operating theatre & bed occupancy based on initial patient visits.
  • Alert and diagnostics from real-time patient data
    • Embedded monitoring devices.
    • Exogenous data from devices to create diagnostic reports for doctors.
  • Survival analysis
    • Analyse survival statistics for different patient attributes (age, blood type, gender etc) and treatments.
  • Medication (dosage) effectiveness
    • Analyse effects of admitting different types and dosage of medication for a disease.
  • Readmission risk
    • Predict risk of re-admittance based on patient attributes, medical history, diagnose and treatment.
  • Claims review prioritisation
    • Payers picking which claims should be reviewed by manual auditors.
  • Medical insurance claim fraud
    • Monitor and predict claims that are likely to be fraud.
  • Prescription compliance
    • Predicting prescription adherence with different approaches to remind patients.
  • Physician attrition
    • Hospitals may want to retain doctors who have admitting privileges in multiple hospitals.

Life Sciences

  • Identifying biomarkers for boxed warnings on marketed products.
  • Predict drug molecule properties based on experimental data from related drug compounds.
  • Drug/chemical discovery & analysis.
  • Analysis of clinical outcomes to adapt clinical trial design.
  • Predicting drug demand in different geographies for different products.
  • Image analysis or other result outputs from research equipments in a high throughput manner.
  • Social media marketing on competitors, patient perceptions, KOL feedback.

Retail/FMCG (Fast-moving consumer goods)

  • Pricing
    • Optimise pricing per time period, per item, per store.
    • Related to supply chain optimisation.
  • Location of new stores
    • Decide location based on consumer demand, traffic, socio-economic factors etc.
  • Product layout in stores
    • This is called planogramming. Planograms refer to visual representations of a store's products or services on display.
  • Merchandising
    • When to start stocking & discontinuing product lines?
  • Inventory management
    • Decide how many units to store in inventory. This is particularly important for perishable goods.
  • Shrinkage analytics
    • Use analytics to reduce or prevent loss due to theft.
  • Warranty analytics
    • Rates of failure for different products.
    • What types of customers buying what types of products are likely to actually redeem a warranty?
  • Market basket analysis
  • Cannibalisation analysis
  • Next best offer analysis
  • In store traffic patterns


  • Claims prediction
    • Predict likelihood of customers making a claim.
    • Might have telemetry data.
  • Claims handling
    • Decide which claim to accept/deny/audit.
    • Manage repairer network (for auto body, doctors etc)
  • Price sensitivity
  • Investments
  • Agent & branch performance

Consumer Financial

  • Financial fraud
    • Banks need to prevent frauds such as credit card fraud.
  • Credit risk
    • Decide whether and how much to lend to individuals/companies.


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


  • Sensor data to detect and/or predict failures.
  • Quality management
    • Identifying out-of-bounds manufacturing using visual inspection/computer vision
  • Demand forecasting/inventory management
  • Warranty/pricing


  • Yield management
    • Take sensor data on soil quality.
    • Determine what seed varieties, seed spacing to use etc.


  • Table/capacity management & reservations
  • Inventory management/dynamic pricing
  • Promotions / Marketing / Upgrades


  • Aircraft/air crew scheduling
  • Seat/gate management
  • Customer complain resolution
  • Maintenance optimisation
  • Tourism demand forecasting


  • Automated essay scoring
  • Student performance/well being monitoring

Real Estate

  • Predicting tenants capacity to pay based on their sales figures and industry.
  • Predicting the best tenant for an open vacancy to maximise overall sales at a mall.


  • Electrical grid distribution
    • Ensure capacity is able to handle peak demand
    • Keep AC frequency as constant as possible
  • Optimise distribution network cost effectiveness
  • Predict commodity requirements

Business Case Study Repositories