A machine learning approach for product matching and categorization

Ristoski, Petar; Petrovski, Petar; Mika, Peter; Paulheim, Heiko

doi:10.3233/sw-180300

Cited by 61 publications

(52 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Moreover, the random forest model gives very good results on all three datasets. With that said, it is to be expected to have better results for both decision tree and random forest with a better feature extraction model as proven in Ristoski et al [42].…”

Section: Product Matching Resultsmentioning

confidence: 95%

“…Finally, in [41], the authors compare various classifiers for product resolution (SVMs, Random Forest, Naive Bayes) with features extracted from a dictionary method and multiple Conditional Random Fields (CRFs) models. The authors, extended their work in [42], where they present extraction models with latent continuous features for product matching and classification, proving that more sophisticated feature extraction methods significantly improve traditional machine learning methods for entity resolution.…”

Section: Related Workmentioning

confidence: 95%

See 1 more Smart Citation

Learning expressive linkage rules from sparse data

Petrovski

Bizer

2020

Self Cite

View full text Add to dashboard Cite

A central problem in the context of the Web of Data, as well as in data integration in general is to identify entities in different data sources that describe the same real-world object. There exists a large body of research on entity resolution. Interestingly, most of the existing research focuses on entity resolution on dense data, meaning data that does not contain too many missing values. This paper sets a different focus and explores learning expressive linkage rules from as well as applying these rules to sparse web data, i.e. data exhibiting a large amount of missing values. Such data is a common challenge in various application domains including e-commerce, online hotel booking, or online recruiting. We propose and compare three entity resolution methods that employ genetic programming to learn expressive linkage rules from sparse data. First, we introduce the GenLinkGL algorithm which learns groups of matching rules and applies specific rules out of these groups depending on which values are missing from a pair of records. Next, we propose GenLinkSA, which employs selective aggregation operators within rules. These operators exclude misleading similarity scores (which result from missing values) from the aggregations, but on the other hand also penalize the uncertainty that results from missing values. Finally, we introduce GenLinkComb, a method which combines the central ideas of the previous two into one integrated method. We evaluate all methods using six benchmark datasets: three of them are e-commerce product datasets, the other datasets describe restaurants, movies, and drugs. We show improvements of up to 16% F-measure compared to handwritten rules, on average 12% F-measure improvement compared to the original GenLink algorithm, 15% compared to EAGLE, 8% compared to FEBRL, and 5% compared to CoSum-P.

show abstract

Section: Product Matching Resultsmentioning

confidence: 95%

Section: Related Workmentioning

confidence: 95%

Learning expressive linkage rules from sparse data

Petrovski

Bizer

2020

Self Cite

View full text Add to dashboard Cite

show abstract

“…They indicated that performance could be improved further using a method that deletes noise data as stopwords. The related works mentioned above regard automatic product classification as a classification problem [19]. Furthermore, a commonality between these works is that they discussed the effect of various input data on classification models.…”

Section: Related Workmentioning

confidence: 99%

Developing Data-Conscious Deep Learning Models for Product Classification

2021

View full text Add to dashboard Cite

In online commerce systems that trade in many products, it is important to classify the products accurately according to the product description. As may be expected, the recent advances in deep learning technologies have been applied to automatic product classification. The efficiency of a deep learning model depends on the training data and the appropriateness of the learning model for the data domain. This is also applicable to deep learning models for automatic product classification. In this study, we propose deep learning models that are conscious of input data comprising text-based product information. Our approaches exploit two well-known deep learning models and integrate them with the processes of input data selection, transformation, and filtering. We demonstrate the practicality of these models through experiments using actual product information data. The experimental results show that the models that systematically consider the input data may differ in accuracy by approximately 30% from those that do not. This study indicates that input data should be sufficiently considered in the development of deep learning models for product classification.

show abstract

“…There are wide range of matching algorithms studied from various string matching (Vandic et al, 2012;Thor, 2010) to more advance methods. We refer the reader to Ristoskia et al (2017) and Kannan et al (2011) for a good brief overview of these studies.…”

Section: Related Workmentioning

confidence: 99%

Neural Network based Extreme Classification and Similarity Models for Product Matching

Shah

Köprü

Ruvini³

2018

Proceedings of the 2018 Conference of the North American Chapter Of the Association for Computational Linguistics: Hu

View full text Add to dashboard Cite

Matching a seller listed item to an appropriate product has become a fundamental and one of the most significant step for e-commerce platforms for product based experience. It has a huge impact on making the search effective, search engine optimization, providing product reviews and product price estimation etc. along with many other advantages for a better user experience. As significant and vital it has become, the challenge to tackle the complexity has become huge with the exponential growth of individual and business sellers trading millions of products everyday. We explored two approaches; classification based on shallow neural network and similarity based on deep siamese network. These models outperform the baseline by more than 5% in term of accuracy and are capable of extremely efficient training and inference.

show abstract

A machine learning approach for product matching and categorization

Cited by 61 publications

References 33 publications

Learning expressive linkage rules from sparse data

Learning expressive linkage rules from sparse data

Developing Data-Conscious Deep Learning Models for Product Classification

Neural Network based Extreme Classification and Similarity Models for Product Matching

Contact Info

Product

Resources

About