ISM3003 – FINAL EXAM STUDY GUIDEChapter 4 - IT for Decision Support#- Agent-based technology (or software agent): it is a type of artificial intelligence - small piece of software that acts on your behalf, performing tasks assigned to it. o 5 main categories: autonomous agent, distributed agent, mobile agent, intelligent agent and multi-agent system- Artificial intelligence: the science of making machines that imitate human thinking and behavior. o 4 main categories – expert systems, neural networks (fuzzy logic), genetic algorithms and agent-based technologies. - Autonomous agent: a type of agent-based technology – software agent that can adapt and alter the manner in which it attempts to achieve its assigned task. - Buyer agent (or shopping agents): it is an information agent on a Website and help you, the consumer, find products and services that you need. - Cartographic (or business geography): when businesses use Geographic Information Systems software to generate maps showing information of interest. - Data management: the data management component of a DSS (Decision Support System) performs the functions of storing and maintaining information and also that of giving you access to information you want your DSS to use. - Data-mining agent: it is an intelligence agent that operates in a data warehouse discovering information. o Most common type of data mining is classification, which finds patterns in info and categorizes items into those classes – neural networks do this the best therefore it’s part of data miningo These agents may detect major shift in a trend or a key indicator, and can detect the presence of new info and alert youo This is important because it can alert the managers early and formulate a plan to protect themselves- Decision support system: any technology-based system would be classified as DSS - highly flexible and interactive IT system that is designed to support decision making when the situation includes no-structured elements. o 3 main objectives: simple and easy to use graphical user interface (GUI), access to large amounts of information, and models and tools (stats + analytical) that you can use to massage the information.- Distributed agent: it is a type of agent-based technology – software agent that works on multiple distinct computer systems- Expert system (or knowledge-based system): it is a type of artificial intelligence – it applies reasoning capabilities to reach a conclusion. o They are good for diagnostic problems (“What’s wrong?”) and prescriptive problems (“What to do?”)o These systems are usually built for s specific application area calleda domain. For example, in accounting for tax planning, auditing or HR to determine whether a company is in compliance with an array of federal employment laws. - Fuzzy logic: it is a type of artificial intelligence that goes with neural networks – is a mathematical method of handling imprecise or subjective information. It assigns values between 0 and 1, to vague or ambiguous information. The higher the value, the closer it is to 1. For example, you might assigned the value of .8 to the value “hot”, then you would construct an algorithm, to describe the interdependence among the variable. o A fuzzy logic algorithm: set of steps that relate variable representing inexact information or personal perceptions. - Genetic algorithm: it is a type of artificial intelligence – it mimics the evolutionary, survival-of-the-fittest process to generate increasingly bettersolutions to problems.- Geographic information systems: it is a type of DSS – designed specifically to analyze spatial information. - Ill-defined: not having a clear description- Implementation: 4th step, APPLY THE FIX – carries out the chose solution,monitor the results, and make adjustments as necessary. Like quality control. o 1st step Intelligence (or diagnostic phase): WHAT TO FIX – find or recognize a problem, need or opportunity. o 2nd step Design: FIND FIXES – consider possible ways of solving the problem, filling the need or taking advantage of the opportunity. You can use the break-even analysis. o 3rd step Choice (or prescriptive phase): PICK A FIX – examine and weigh the merits of each solution, estimate the consequences of each and choose the best one (which may be to do nothing at all). The best solution may depend on costs, ease of implementation, staffing requirements and timing. o NOTE: the 4 phase process is not necessarily linear; you may find ituseful or necessary to cycle back to an earlier phase. For example, in the CHOICE phase you may find another possible solution, so youwould have to go back to the DESIGN phase, include the newlyfound solution, return to the CHOICE phase and compare the new solutions to the others that you generated. - Information agent: it is a type of intelligent agent - that searches for information of some kind and brings it back. For example, a buyer agent or shopping agent. - Intelligent agent: it is a type of agent-based technology – incorporates artificial intelligence capabilities such as learning and reasoning to assist you, or act on your behalf, in performing repetitive computer-related tasks. - Knowledge management system: another word for expert systems- Machine intelligence: another word for artificial intelligence- Model management: The model management component of a wide variety of statistical and analytical tools, techniques, and models. These will depend greatly on the decision-making task at hand. - Monitoring-and-surveillance agent: it is a type of intelligent agent – constantly observes and reports on some entity of interest, a network, or manufacturing equipment. - Multi-agent system: it is a type of agent-based technology – group of intelligent agents that have the ability to work independently but must also work with each other in order to achieve their assigned task. o These are being used to model stock market fluctuations or even predict the escape routes that people seek in a burning building. - Neural network (artificial neural network or ANN): it is a type of artificial intelligence – capable of finding and differentiating patterns. It learns by example and can adapt to new concepts and knowledge. o They are used for visual patterns and speech recognition systemso Most useful for identification, classification and predictions when a vast amount of information is available. - Predictive agents (or predictive analytics):