Data Fusion and Data Quality

The recent development of the Internet has made an increasing number of information sources available to users. This makes it necessary to submit queries only to the most appropriate sources. When gathering and combining information from these sources the quality ooered can and must be a criterion for source selection. However, information quality has many dimensions and it is thus diicult to directly compare sources with one another or give a ranking of sources. Selecting the best sources is thus a multiple attribute decision problem. After introducing four techniques of multiple attribute decision making we apply them to the problem of quality-driven selection of sources: The Simple Additive Weighting method (SAW), the TOPSIS method, the Analytical Hierarchy Process method (AHP) and the Data Envelopment Analysis method (DEA). We analyze and compare these methods with respect to the assumptions they are based on, their discretionary value and user interaction. 1 Motivation The development of the Internet and the World Wide Web during recent years has made it possible and useful to access many diierent information