Transcript Slide 1
CHAPTER 4 ANALYTICS, DECISION SUPPORT, AND ARTIFICIAL INTELLIGENCE Brainpower for Your Business Opening Case: Online Learning Notice the increase in online learning and the decrease in traditional enrollments. What are the causes of this: Universities offering more online classes? More alternatives to Universities? What are the business implications of this? More space on campus…what can be done with that if it becomes available? Should colleges move towards online courses? Phases of Decision Making Intelligence (diagnostic) Design (create solutions) Choice (select solution) Implementation (apply solution) May cycle between these phases. Types of Decisions Structured decision : data is available and variables are known. Decision is based on known criteria. Semi-Structured decision: In between. Some uncertainty. Nonstructured decision: not sure what data to collect.Variables affecting decision are not known. Not sure what the success criteria may be. Satisficing: Not optimal decision but allows us to satisfy predetermined Criteria. E.g., Salary at least $50,000. Types of Decisions Recurring decision Nonrecurring (ad hoc) decision Decision Support Systems Helps you analyze, but you must know how to solve the problem, and how to use the results of the analysis Model management component Data management component User interface management component Components of a DSS Geographic Information Systems Geographic information system (GIS) Spatial information is any information in map form Used to analyze information, generate business intelligence, and make decisions. It’s easier to see information on a map. Suppose you are going to start a new store selling electronic accessories. Where would you locate it? www.historypin.com https://www.youtube.com/watch?v=NqUSfjTSLyo https://www.youtube.com/watch?v=tnRJaHZH9lo DATA-MINING TOOLS AND MODELS ◦ Databases and DBMSs: operational data ◦ Multidimensional analysis tools: summarized data ◦ Digital dashboards: managers can get realtime info and drill down or roll up ◦ Statistical tools: regression, summarization, association rules, clustering ◦ GISs: See information on a map ◦ Artificial intelligence: Genetic algorithms, neural nets Data-Mining: Predictive Analytics Predictive analytics ◦ highly computational data-mining technology that uses information and business intelligence to build a predictive model for a given business application Insurance, retail, healthcare, travel, financial services, CRM, SCM, credit scoring, etc Data-Mining: Predictive Analytics Example Prediction goal ◦ What customers are most likely to respond to a social media campaign within 30 days by purchasing at least 2 products in the advertised product line? Prediction indicators ◦ ◦ ◦ ◦ Frequency of purchases Proximity of date of last purchase Presence on Facebook and Twitter Number of multiple-product purchases Data-Mining: Text Analytics Text analytics ◦ uses statistical, AI, and linguistic technologies to convert unstructured textual information into structured information Gaylord Hotels uses text analytics to make sense of customer satisfaction surveys Data-Mining: Endless Analytics Web analytics – understanding and optimizing Web page usage ◦ Search engine optimization (SEO) – improving the visibility of Web site using tags and key terms HR analytics – analysis of human resource and talent management data Marketing analytics – analysis of marketing-related data to improve product placement, marketing mix, etc Data-Mining: Endless Analytics CRM analytics – analysis of CRM data to improve sales force automation, customer service, and support Social media analytics – analysis of social media data to better understand customer/organization interaction dynamics Mobile analytics – analysis of data related to the use of mobile devices to support mobile computing and mobile e-commerce (m-commerce) Artificial Intelligence Artificial intelligence (AI) Types of AI systems used in business 1. 2. 3. 4. Expert systems Neural networks Genetic algorithms Agent-based technologies AI systems deliver the conclusion (rather than helping you analyze the options) Expert Systems Expert (knowledge-based) system Uses if-then rules…lots of them. Used for ◦ Diagnostic problems (what’s wrong?) ◦ Prescriptive problems (what to do?) E.g., should we give a loan to someone. Or should a credit card customer be allowed to run a charge? If customer older than 40 AND customer income > 100,000 and previous payments all on time THEN allow transaction. Expert System: Components 1. Information Types ◦ ◦ ◦ 2. People ◦ ◦ ◦ 3. Problem facts Domain expertise “Why?” information Domain expert: know the rules to apply Knowledge engineer: Capture the rules Knowledge worker: use the rules IT Components ◦ ◦ ◦ ◦ ◦ Knowledge acquisition Knowledge base Inference engine User interface Explanation module Expert System: Components What Expert Systems Can and Can’t Do An expert system can ◦ Reduce errors ◦ Improve customer service ◦ Reduce cost An expert system can’t ◦ Use common sense ◦ Automate all processes Neural Networks and Fuzzy Logic Neural network (NN) (or artificial neural network (ANN)) Learns through training data Finds patterns Different from expert systems since rules do not have to be spelled out here…it discovers its own rules in the data! The Layers of a Neural Network Neural Networks Can… Learn and adjust to new circumstances on their own Take part in massive parallel processing Function without complete information Cope with huge volumes of information Analyze nonlinear relationships Fuzzy Logic Fuzzy logic ◦ a mathematical method of handling imprecise or subjective information Used to make ambiguous information such as “short” usable in computer systems Applications ◦ Google’s search engine ◦ Washing machines ◦ Antilock brakes Genetic Algorithms Genetic algorithm (GA) Takes thousands or even millions of possible solutions, combining and recombining them until it finds the an optimal solution Needs a fitness function and encoding of the possible solutions in terms of chromosomes. It then attempts to find the best chromosomes, after reproduction and mutation. E.g., What is the best inventory level for engines for the Ford F150? Work in environments where no model of how to find the right solution exists Agent-Based Technologies Intelligent Agents Multi-Agent Systems Intelligent Agents Software that acts on our behalf ◦ ◦ ◦ ◦ Information agents or shopping/buyer agents Monitoring-and-surveillance agents User or personal agents Data-mining agents Multi-Agent Systems Biomimicry Swarm (collective) Intelligence. Ants find shortest route to food by laying pheromone trails that decay automatically if they are unfit or the food supply is gone. Based on this, they find theshortest path to the food. Similarly, find simple rules that can create big desirable patterns.