Case-Based Reasoning in E-CommerceWhat is E-Commerce?How can CBR help?Slide 4What’s wrong?We have a problemSlide 7Some Preliminary InfoIndividual Wish PropertiesSlide 10Overall Wish PropertiesProduct ClassificationsHow Do These Properties Help?Transaction ModelPre-SalesSlide 16ExampleHow Does It Work?SalesNegotiationSlide 21Slide 22Slide 23After-SalesSlide 25SummaryReferencesCase-Based Reasoning in E-CommerceJoe SoutoCSE 435What is E-Commerce?“The exchange of information, goods, or services through electronic networks”1How can CBR help?How many times have you seen this?How can CBR help?Or this?What’s wrong?Demand is either over-specified or under-specifiedIt is up to the user to find what they wantThere is no intelligent sales supportWe have a problemBuyer has limited knowledge of product baseSeller has limited knowledge of buyer’s requirements”Knowledge Gap”We have a problemKnowledge gap is solved in real-life by a human sales agent as a mediator. We don’t have this luxury online.Solution: CBR approach product knowledge is stored as experience in a case base. Sales agent makes recommendations based on the stored experience.Some Preliminary InfoWe need a way to define user requirementsCustomers buy items in order to satisfy their desiresDefine a customer’s desire as a “Wish”Wishes have various propertiesIndividual Wish PropertiesImportanceHard: MUST be met (ie: “vacation for <$2000”)Soft: not essential, but helpful (ie: “red” car)Agent must satisfy ALL hard req’s and as many soft as possiblePrecisionPrecisely Determined (specific, ie: “>3GHz P4”)Undetermined (vague, ie: “fast processor”)Individual Wish PropertiesCertaintyCertainUncertainSales agent must try to increase certainty of wishes and make recommendations based on themOverall Wish PropertiesRedundancyWishes can be redundantEx: Computer that’s “fast” and can play Half-Life 2Agent must recognize and avoid redundant inquiriesConsistencyWishes can be contradictory Ex: new Ferrari, and under $1000Agent must either ask user to clarify, or suggest products that satisfy one of the two wishesProduct ClassificationsHow Do These Properties Help?1. Customers want a product to satisfy a wish2. Products have various properties3. Therefore, product properties can be mapped to the satisfaction of a customer’s wishWith all that in mind, now we can look at the transaction processTransaction ModelSingle transaction can be modeled with three phasesPre-SalesBuyer wants a product, Seller provides information3 PhasesSupplier SearchClient determines which supplier can satisfy their wishesProduct SearchMapping of customer criteria to productsNegotiation1. Price and way of payment 2. Details of delivery 3. Regulations about cost and deliveryPre-SalesRecall the Google ExampleNo “intelligent sales support”Burden of knowledge is in hands of the customersExampleDue to Knowledge Gap, Analog Devices added a CBR system to assist Pre-SalesAnalog Devices:http://www.analog.comHow Does It Work?Similarity Metrics!Similarity function for single attributeOK to be under, less similar if over desired valueThe overall similarity is computed weighted average of local similarities.Remember the “priority” boxSalesProduct has been chosen, must be configured and paid forCustomer and Sales Agent negotiate about product attributes and costs Intelligent Support is needed for negotiationNegotiation“A process where two parties bargain resources for an intended gain”1In Sales phase, customers navigate through products to satisfy their wish. Some wishes known, others discovered in the process. Hard wishes must be fulfilled, soft wishes can be negotiated. Agent finds out these demands with the customer and finds a product which fulfills them. Agent can be “Active” or “Passive”SalesCBR Model must be modifiedStandard Model:2. Reuse3. Revise4. RetainCase Library1. RetrieveBackground KnowledgeSalesNew ModelNo Retain phase: sale does not add another product to the product baseAdd Refine phase: user demands refined based on the evaluations given by the customer.ExampleCBR approach to negotiating a BMW saleAgent here is passiveButtons for “sportier”, “more comfortable”, “cheaper”, etc.After-SalesCustomer has already bought a product and needs support during its usageTo assist the customer, they are supported with a case base of possible product problems, a query interface, and similarity measures which should help to find a similar problem and solutionMany companies have online CBR customer-support websites (Dell, 3Com, etc) Help Desk SystemsExampleDell Support site:http://support.dell.comSummaryE-commerce is a growing field with lots of potential revenueStandard search technology is too limitedCBR can be applied in all 3 transaction phasesKey is to provide intelligent sales support agent guides customer through each phase of transactionReferences1. “Intelligent Sales Support with CBR”Wilke, Lenz, Wess2. “Experience Management for Electronic Commerce”Bergmann3. Wikipedia:
View Full Document