DECISION SUPPORT SYSTEMS

A Decision Support System (DSS) is an interactive information system that provides information, models and data manipulation tools to help make decisions in semi structured and unstructured situations where no one knows exactly how the decision should be made. The traditional DSS approach includes interactive problem solving direct use of models, and user-controllable methods for displaying and analyzing data and in formulating and evaluating alternative decisions. This approach grew out of dissatisfaction with the traditional limitations of TPS and MIS. TPS focused on record keeping and control of repetitive clerical processes. MIS provided reports for management but were often inflexible and unable to produce the information in a form in which managers could use it effectively. In contrast, DSSs were intended to support managers and professionals doing largely analytical work in less structured situation with unclear criteria for success. DSSs are typically designed to solve the structured parts of the problem and help isolate places where judgment and experience are required. 

DSSs may report repetitive or non-repetitive decision-making. They support repetitive decision making by defining procedures and formats, but they still permit the users to decide how and when to use the system’s capabilities. They support non-repetitive decision making by providing data, models and interface methods that can be used however the user wants. The broad spectrum of information systems with the DSS label range from general tools such as spreadsheets, data analysis, and graphics packages to highly customized simulation or optimization models focusing on a specific business situation. 

OLAP and Data Mining

The use of online data analysis tools to explore large databases of transaction data is called Online Analytical Processing (OLAP). The idea of OLAP grew out of difficulties analyzing the data in databases that were being updated continually by online transaction processing systems. When the analytical processes accessed large slices of the transaction database, they slowed down transaction processing critical to customer relationships. The salutation was periodic downloads of data from the active transaction processing database into a separate database designed specifically to support analysis work. The separate database often resides on a different computer, which together with its specialized software is called a data warehouse. 

Downloading data to a data warehouse makes it possible to perform both transaction processing and analytical processing efficiently without mutual interference. Data mining is the use of data analysis tools to try to find the patterns in large transaction databases such as the customer receipts generated in a large sample of grocery stores across the United States. Careful analysis of this data might reveal patterns that could be used for marketing promotions, such as a correlation between diaper sales and beer sales during the evening hours.