Alvaro Bolivar

Keyword extraction for contextual advertisement

As the largest online marketplace, eBay strives to promote its inventory throughout the Web via different types of online advertisement. Contextually relevant links to eBay assets on third party sites is one example of such advertisement avenues. Keyword extraction is the task at the core of any contextual advertisement system. In this paper, we explore a machine learning approach to this problem. The proposed solution uses linear and logistic regression models learnt from human labeled data, combined with document, text and eBay specific features. In addition, we propose a solution to identify the prevalent category of eBay items in order to solve the problem of keyword ambiguity.

Substitutes or complements: another step forward in recommendations

In this paper, we introduce the method tagging substitute-complement attributes on miscellaneous recommending relations, and elaborate how this step contributes to electronic merchandising. There are already decades of works in building recommender systems. Steadily outperforming previous algorithms is difficult under the conventional framework. However, in real merchandising scenarios, we find describing the weight of recommendation simply as a scalar number is hardly expressive, which hinders the further progress of recommender systems. We study a large log of user browsing data, revealing the typical substitute complement relations among items that can further extend recommender systems in enriching the presentation and improving the practical quality. Finally, we provide an experimental analysis and sketch an online prototype to show that tagging attributes can grant more intelligence to recommender systems by differentiating recommended candidates to fit respective scenarios.

Predicting the conversion probability for items on C2C ecommerce sites

Online ecommerce has been booming for a decade. For instance, as the largest online C2C marketplace (eBay), millions of new items are listed daily. Due to the overwhelming number of items, the process of finding the right items to buy is sometimes daunting. In order to address this problem, this paper describes the idea of predicting the probability that a newly listed item will be sold successfully. And adjust the item exposure chances proportional according to their conversion possibility. Hence, by ranking higher items that users are likely to buy, the chance that users make the purchases could be increased as well as their user satisfaction. For catalog products that have been listed repeatedly, this probability can be measured empirically. However, on C2C sites like eBay, lots of items are not product-based. They are unique, and from different sellers. Therefore, in order to predict whether a new listing will be sold, we collect a large scale item set as the training data, and a set of features were used to model the average buyer shopping decision on C2C sites. Experimental results verified our systems feasibility and effectiveness.

The effect of title term suggestion on e-commerce sites

Most E-Commerce websites rely on title keyword search to accurately retrieve the items for sale in a particular category. We have found that the titles of many items on eBay are shortened or not very specific, which leads to ineffective results when searched. One possible solution is to recommend the sellers relevant and informative terms for title expansion without any change of search function. The related technique has been explored in previous work such as query expansion and keyword suggestion. In this paper, we study the effect of term suggestion on title-based search. A frequently used approach, co-occurrence, is tested on a dataset collected from eBay website (www.ebay.com). Besides, for suggestion algorithm, we take into account three particular features in our application scenario, including concept term, description relevance and chance-to-be viewed. Although the experiments are conducted on eBay data, we believe that considering E-Commerce particularities will help us to customize the suggestion according to the requirements of web commerce.

Rare item detection in e-commerce site

As the largest online marketplace in the world, eBay has a huge inventory where there are plenty of great rare items with potentially large, even rapturous buyers. These items are obscured in long tail of eBay item listing and hard to find through existing searching or browsing methods. It is observed that there are great rarity demands from users according to eBay query log. To keep up with the demands, the paper proposes a method to automatically detect rare items in eBay online listing. A large set of features relevant to the task are investigated to filter items and further measure item rareness. The experiments on the most rarity-demand-intensitive domains show that the method may effectively detect rare items (>90% precision).