DataDetective is Sentient’s data mining software product. DataDetective helps organizations become more effective by enabling them to run deep analyses on their complete data. Advanced analysis technologies make finding relationships, patterns and trends a quick and easy job. This gives users more insight and allows them to create better forecasts. The most important functionalities in DataDetective are: predicting, clustering, finding relationships, profiling, network analysis, fuzzy matching, creating graphs, creating maps, defining selections and creating cross tables (OLAP).
DataDetective actively supports the user in applying the built-in data mining techniques, thereby replacing technology-oriented work by task-oriented work. Applicable techniques are chosen and configured in a way that best suits the data to be analyzed. This makes the software accessible for a large group of people and ensures efficient application of data mining.
Return on investment
Because of the ease-of-use and speed of DataDetective, every organization can start applying data mining technology with a minimal investment of time and effort. The software is designed to remove the need for a statistician or data mining specialist. Using data mining during meetings prevents costly delays in decision-making. The superior quality of the analyses and forecasts ensure optimal return on investment.
Scalable and automatic
DataDetective can handle a large variety of data sources, containing millions of records and thousands of variables. Restricting the analysis to a small subset of records and variables is no longer required. DataDetective users can simply tell the program to find all relevant patterns and relationships in the complete data set. After this, further analysis can be performed on the most promising initial results.
Intelligence depends largely on the ability to associate: Which things look alike? Which comparable situations and aspects are relevant? This ability is also the core of DataDetective and is applied, in the shape of fuzzy matching, to search intelligently, to find clusters, and to make forecasts based on a self-learning process. The quality of self-learning associative forecasting models is much higher than standard statistical models. An important advantage of fuzzy matching is the lack of strict requirements on the data format: items may be missing from records. Complex datatypes, such as free text and data collections, can be included in the matching process.
DataDetective supports datawarehouses with multiple fact tables containing millions of records and thousands of columns each.
Examples of such datawarehouses:
NOM (consumer data), 13,000+ records, with 2,500+ columns, stored in Access
Amsterdam police: 4,000,000+ incidents with 170+ columns, 4,000,000+ actions with 170+ columns, 2,000,000+ persons with 210+ columns, stored in SQL Server
Data can be imported from:
Excel, SPSS, text files, any ODBC database
Results can be exported to:
Excel, PowerPoint, MapInfo, MapAnalyse, Google Maps, SPSS, Analyst’s Notebook, text files, XML
Supported datawarehouse storage:
SQL Server, Access, Oracle, Sybase
Windows 7 and newer, including all Windows Server versions and Citrix