Average Reviews:
(More customer reviews)This book can be read as a sequel to an earlier text, Statistical Methods in e-Commerce Research (Statistics in Practice). That looked at various types of websites, like Amazon and Wikipedia, while the current offering specialises to the key case of studying auction websites. Of these, eBay dominates the discussion, simply because it is the largest such website on the Internet. In a way, the exposition is simpler than it might have been just a few years ago, when Amazon and Yahoo also ran auctions. They were keying off eBay's success and hoped to take some of that business. But their efforts came to nought, so that now if you study online auctions, it is really only eBay and a handful of much smaller entities like uBid.
The screen captures in chapter 2 of typical web pages from an auction [on eBay] shows the complex spaghetti-like source code. Note that if you do decide to screen scrape, then this is brittle, since if the website makes just minor changes in the format of their pages, extensive changes to your parsing might be necessary, to extract the same information. But as the authors make clear, screen scraping has the advantage of being free. An alternative is to use a Web Service, if that is offered by the website. Much more efficient and robust. But not all websites have this, and those that do could require payment. Plus the information offered by their Web Service might not include data that you need.
Chapter 3 tackles the problem of how to simulate data using continuous distributions, when actual auction data often looks like a mixture of continuous and spiky inputs, where the latter are bids of high frequency, that stand significantly above the rest of the bid distribution.
Chapter 4 discusses various models - exponential, log, logistic and inverse logistic, that can be used to model a given auction. But the problem is that across a set of auctions, even for instances of the same item being offered, all such models might be observed. Where a specific auction could be best fitted by a log, say, while another auction looks like a logistic. The authors suggest a "Beta()" function that has only 2 parameters. This turns out to be easy to compute, and, depending on the choices of parameter values, can replicate each of the 4 earlier models. Just as importantly, the fitting of a Beta to a given auction can be automated, which gets around an earlier problem of having to make a manual choice between one of the earlier models.
Perhaps as interestingly, the chapter goes further, into studying what the book calls the spatial similarity between auctions. The spatial refers to auctions where items differ slightly. For example, a gaming computer that has different colours, and different disk sizes and different memory sizes installed. This is a multidimensional feature space, where the features might differ continuously [like memory] or discretely [like colour]. It reflects the well known attraction of eBay where if you search for a popular item, you can find hundreds [or even thousands] that differ in parameters like these. Modelling the behaviour of bidders when confronted by a surfeit of choices would be good. The authors show a way to tackle how to define a metric in the feature space.
Click Here to see more reviews about:
Modeling Online Auctions (Statistics in Practice)Explore cutting-edge statistical methodologies for collecting, analyzing, and modeling online auction data
Online auctions are an increasingly important marketplace, as the new mechanisms and formats underlying these auctions have enabled the capturing and recording of large amounts of bidding data that are used to make important business decisions. As a result, new statistical ideas and innovation are needed to understand bidders, sellers, and prices. Combining methodologies from the fields of statistics, data mining, information systems, and economics, Modeling Online Auctions introduces a new approach to identifying obstacles and asking new questions using online auction data.
The authors draw upon their extensive experience to introduce the latest methods for extracting new knowledge from online auction data. Rather than approach the topic from the traditional game-theoretic perspective, the book treats the online auction mechanism as a data generator, outlining methods to collect, explore, model, and forecast data. Topics covered include:
Data collection methods for online auctions and related issues that arise in drawing data samples from a Web site
Models for bidder and bid arrivals, treating the different approaches for exploring bidder-seller networks
Data exploration, such as integration of time series and cross-sectional information; curve clustering; semi-continuous data structures; and data hierarchies
The use of functional regression as well as functional differential equation models, spatial models, and stochastic models for capturing relationships in auction data
Specialized methods and models for forecasting auction prices and their applications in automated bidding decision rule systems
Throughout the book, R and MATLAB software are used for illustrating the discussed techniques. In addition, a related Web site features many of the book's datasets and R and MATLAB code that allow readers to replicate the analyses and learn new methods to apply to their own research.
Modeling Online Auctions is a valuable book for graduate-level courses on data mining and applied regression analysis. It is also a one-of-a-kind reference for researchers in the fields of statistics, information systems, business, and marketing who work with electronic data and are looking for new approaches for understanding online auctions and processes.
Visit this book's companion website by clicking here
Get 16% OFF
Click here for more information about Modeling Online Auctions (Statistics in Practice)
