Dynamically creating indices for two million cases: A real world problem

Daengdej, Jirapun; Lukose, Dickson; Tsui, Eric; Beinat, Paul; Prophet, Laura

doi:10.1007/bfb0020605

Cited by 23 publications

(13 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, calculating metrics such as number of visitors or page views for a social media or e-commerce web site with hundreds of million users is a common practice at industry, but in current CBR research, experiments with tens of thousands of cases, or even much fewer, are common. Few CBR projects have considered scales up to millions of cases [14,15], and to our knowledge, none have explored larger scales except a few exceptions such as a recent effort to apply big data methods focused on exact match only, rather than similarity-based retrieval [15].…”

Section: Scaling Cbr To Big Datamentioning

confidence: 99%

CBR Meets Big Data: A Case Study of Large-Scale Adaptation Rule Generation

Jalali

Leake

2015

Case-Based Reasoning Research and Development

View full text Add to dashboard Cite

Abstract. Adaptation knowledge generation is a difficult problem for CBR. In previous work we developed ensembles of adaptation for regression (EAR), a family of methods for generating and applying ensembles of adaptation rules for case-based regression. EAR has been shown to provide good performance, but at the cost of high computational complexity. When efficiency problems result from case base growth, a common CBR approach is to focus on case base maintenance, to compress the case base. This paper presents a case study of an alternative approach, harnessing big data methods, specifically MapReduce and locality sensitive hashing (LSH), to make the EAR approach feasible for large case bases without compression. Experimental results show that the new method, BEAR, substantially increases accuracy compared to a baseline big data k-NN method using LSH. BEAR's accuracy is comparable to that of traditional k-NN without using LSH, while its processing time remains reasonable for a case base of millions of cases. We suggest that increased use of big data methods in CBR has the potential for a departure from compression-based case-base maintenance methods, with their concomitant solution quality penalty, to enable the benefits of full case bases at much larger scales.

show abstract

Section: Scaling Cbr To Big Datamentioning

confidence: 99%

CBR Meets Big Data: A Case Study of Large-Scale Adaptation Rule Generation

Jalali

Leake

2015

Case-Based Reasoning Research and Development

View full text Add to dashboard Cite

show abstract

“…The underlying algorithms and data structures supporting these algorithms, however, typically depend upon a relatively small and/or static number of case/cue dimensions, and do not take advantage of the temporal structure inherent to episodic memories. Considerable work has been expended to explore heuristic methods that exchange reduced competency for increased retrieval efficiency [19], including refined indexing [2] [3], storage reduction [25], and case deletion [17]. Many researchers achieve gains through a two-stage cue matching process that initially considers surface similarity, followed by structural evaluation [4].…”

Section: Related Case-based Reasoning Workmentioning

confidence: 99%

Efficiently Implementing Episodic Memory

Derbinsky

Laird

2009

Case-Based Reasoning Research and Development

View full text Add to dashboard Cite

Abstract. Endowing an intelligent agent with an episodic memory affords it a multitude of cognitive capabilities. However, providing efficient storage and retrieval in a task-independent episodic memory presents considerable theoretical and practical challenges. We characterize the computational issues bounding an episodic memory. We explore whether even with intractable asymptotic growth, it is possible to develop efficient algorithms and data structures for episodic memory systems that are practical for real-world tasks. We present and evaluate formal and empirical results using Soar-EpMem: a task-independent integration of episodic memory with Soar 9, providing a baseline for graph-based, taskindependent episodic memory systems.

show abstract

“…Others still have proven to be too labor intensive to be of practical use in real-world domains. For example, Deangdej et al 21 devised a dynamic indexing structure to retrieve cases at run time from a case base of over two million cases in an insurance domain. This is an interesting approach in that indexes are generated dynamically in real time in response to target problems.…”

Section: Introductionmentioning

confidence: 99%

Assessment of four modifications of a novel indexing technique for case-based reasoning

Galushka

Patterson

Nugent

2007

Int. J. Intell. Syst.

View full text Add to dashboard Cite

Benefits of using D-HS include ease of case and similarity knowledge maintenance, simplicity, accuracy, and speed in comparison to conventional approaches widely used in CBR. We present results from the analysis of 20 case bases for classification problems and 15 case bases for regression problems. We demonstrate the improvements in accuracy and/or efficiency of each D-HS modification in comparison to traditional k-NN, R-tree, C4,5, and M5 techniques and show it to be a very attractive approach for indexing case bases. We also illuminate potential areas for further improvement of the D-HS approach.

show abstract

Dynamically creating indices for two million cases: A real world problem

Cited by 23 publications

References 12 publications

CBR Meets Big Data: A Case Study of Large-Scale Adaptation Rule Generation

CBR Meets Big Data: A Case Study of Large-Scale Adaptation Rule Generation

Efficiently Implementing Episodic Memory

Assessment of four modifications of a novel indexing technique for case-based reasoning

Contact Info

Product

Resources

About