Monitoring Change in Mining Results

Baron, Steffan; Spiliopoulou, Myra

doi:10.1007/3-540-44801-2_6

Cited by 12 publications

(23 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Incremental approaches generally address the problem of finding new rules that have emerged with the changes in the dataset, and removing previously discovered rules that may no longer be significant due to the changes in the data. Baron and Spiliopoulou [Baron and Spiliopoulou 2001] however argue that a rule may be significant at a point in time, disappear at a later point in time, and reappear much later. Thus, discovered rules may have inherent temporal characteristics.…”

Section: Related Workmentioning

confidence: 90%

“…Most of the research works on navigational pattern discovery, however, are in the area of web usage mining. Baron and Spiliopoulou [Baron and Spiliopoulou 2001] present a framework for monitoring temporal dynamics of discovered rules. Researchers have long acknowledged that rules change over time once the underlying data sources change.…”

Section: Related Workmentioning

confidence: 99%

“…can be designed with increased robustness if the temporal trends and characteristics of the patterns are taken into consideration. Some recent works have addressed the problem of modeling patterns as temporal objects [Baron and Spiliopoulou 2001;Jin et al 2002]. The techniques proposed in these works achieve partial temporal modeling of patterns (i.e., they do not represent patterns as full time series data with data points for each time unit).…”

mentioning

confidence: 99%

See 2 more Smart Citations

A framework for representing navigational patterns as full temporal objects

2004

View full text Add to dashboard Cite

Navigational patterns have applications in several areas including: web personalization, recommendation, userprofiling and clustering, etc. Most existing works on navigational pattern-discovery give little consideration to the effects of time (or temporal trends) on navigational patterns. Some recent works have proposed frameworks for partial temporal representation of navigational patterns. This paper proposes a framework that models navigational patterns as full temporal objects that may be represented as time series. Such a representation allows a rich array of analysis techniques to be applied to the data. The proposed framework also enhances the understanding and interpretation of discovered patterns, and provides a rich environment for integrating the analysis of navigational patterns with data from the underlying organizational environments and other external factors. Such integrated analysis is very helpful in understanding navigational patterns (e.g., E-commerce sites may integrate the trend analysis of navigational patterns with other market data and economic indicators). To achieve full temporal representation, this paper proposes a navigational pattern-discovery technique that is not based on pre-defined thresholds. This is a shift from existing techniques that are driven by pre-defined thresholds that can only support partial temporal representation of navigational patterns.

show abstract

Section: Related Workmentioning

confidence: 90%

Section: Related Workmentioning

confidence: 99%

mentioning

confidence: 99%

See 1 more Smart Citation

A framework for representing navigational patterns as full temporal objects

2004

View full text Add to dashboard Cite

show abstract

“…The abstraction of time series into sequences of events or time intervals approximates the time series piecewise by functions (so do [12,34,35]). Event sequences are investigated in order to predict events or to determine correlations of events [15,9,11,13,36]. The approach of Frank Höppner abstracts time series to time intervals and uses the time relations of James Allen in order to learn episodes [23,22].…”

Section: Related Work and Conclusionmentioning

confidence: 99%

“…We were provided with time-stamped data from the Swiss Life insurance company. There are many ways to handle time-related data, e.g., [8][9][10][11][12][13]. It is hard to select the appropriate approach [14].…”

Section: Introductionmentioning

confidence: 99%

Analysing Customer Churn in Insurance Data – A Case Study

Morik

Köpcke

2004

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. Designing a new application of knowledge discovery is a very tedious task. The success is determined to a great extent by an adequate example representation. The transformation of given data to the example representation is a matter of feature generation and selection. The search for an appropriate approach is difficult. In particular, if time data are involved, there exist a large variety of how to handle them. Reports on successful cases can provide case designers with a guideline for the design of new, similar cases. In this paper we present a complete knowledge discovery process applied to insurance data. We use the TF/IDF representation from information retrieval for compiling time-related features of the data set. Experimental reasults show that these new features lead to superior results in terms of accuracy, precision and recall. A heuristic is given which calculates how much the feature space is enlarged or shrinked by the transformation to TF/IDF.

show abstract

Temporal Evolution and Local Patterns

Spiliopoulou

Baron

2005

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Monitoring Change in Mining Results

Cited by 12 publications

References 8 publications

A framework for representing navigational patterns as full temporal objects

A framework for representing navigational patterns as full temporal objects

Analysing Customer Churn in Insurance Data – A Case Study

Temporal Evolution and Local Patterns

Contact Info

Product

Resources

About