Advances in Knowledge Discovery in Databases

Knowledge discovery in databases (KDD) is a well known research area in computer science. It has been marching ahead rapidly since its inception in late 1980s and has come to prominence over the last two and half decades as a discipline in its own right. With the advancements of hardware technologies, it is now feasible to collect large amount of data within a short span of time, and process them within a reasonable time limit. There are many areas of data mining that offer challenges and opportunities. This book presents some advancement in the areas on market basket database, time-stamped databases and multiple related databases. Market basket data analysis started at the beginning, and journey continues till now. Many interesting and intelligent algorithms are reported on data mining tasks. Also, a large number of association measures are invented over time, and that play significant roles in decision support applications. Mining time-stamped data has become a natural activity as real databases are dynamic, and hence grow over time, and it will continue to dominate in future. Time-based data analyses and identifying temporal patterns are two major activities in this domain. Mining multiple related databases is relatively a recent topic of data mining. Numerous problems are being reported in these days. Local patterns analysis provides a way to mine multiple large databases reasonably well. Most of the recent developments in these three domains are discussed, analyzed, and contrasted.