What eBay's Machine Learning Advances Can Teach IT Professionals - InformationWeek

InformationWeek is part of the Informa Tech Division of Informa PLC

This site is operated by a business or businesses owned by Informa PLC and all copyright resides with them.Informa PLC's registered office is 5 Howick Place, London SW1P 1WG. Registered in England and Wales. Number 8860726.

IoT
IoT
Data Management // Big Data Analytics
News
9/6/2016
08:06 AM
Connect Directly
Twitter
RSS
E-Mail
50%
50%

What eBay's Machine Learning Advances Can Teach IT Professionals

EBay has been gathering data and employing machine learning to connect more buyers to sellers and increase the trustworthiness of transactions. The use-cases are worth exploring for any IT professional looking to help improve a company's bottom line by applying machine learning to its customer-facing applications.

13 Ways Machine Learning Can Steer You Wrong
13 Ways Machine Learning Can Steer You Wrong
(Click image for larger view and slideshow.)

eBay is applying the lessons of machine learning to improve the ways customers interact with the site. For four years, eBay has been collecting customer search data, along with search click-through rates and other customer interaction data, and feeding the information into its machine learning system.

In an interview with InformationWeek, Dan Fain, the company's VP of engineering, outlined the steps being taken, and the business motivation behind them. The use-cases are worth exploring for any IT professional looking to help improve a company's bottom line by applying machine learning to customer-facing applications.

Search, customer click patterns, language translations, item recommendations, and image analysis are among the key ways machine learning is being put to use at eBay, according to Fain.

[Want to see how eBay has already pioneered the use of big data? Read How eBay's Kylin Tool Makes Sense of Big Data.]

The first, and most important, application of machine learning is to improve search functions on eBay.com, according to Fain. "We have several machine learning models working behind the scenes to ensure we get the best search results," said Fain in our interview.

With more than 1 billion items for sale, many things can go wrong in a search on eBay. For example, much depends upon the words and phrasing chosen by the customer. For example, when someone searches "sewing machines," he or she probably wants a tool with which to do their own sewing.

But machine learning has shown that people are sometimes looking for a sewing machine their grandmother used to use, or even a "collectible" to fit into a set of machines with meaning to the collector.

The search triggers a check of eBay's inventory of sewing machine models for sale. The machine learning models may be able to gauge some intent from the history of the visitor doing the asking. They also check the behavior of other visitors searching for a sewing machine on the site. Did they browse and go away? Did they stop when they found a modern model? In what ways did antique sewing machine hunters display their interest?

Fain cited another search phrase, "Swiss watch with leather straps," which raises different challenges for the site that machine learning can address. A normal search would return a long list of Swiss watches and an equally long list of leather bands. If the person doing the search wants those two things as one product, such search results will not be very useful.

(Image: eBay. The eBay Inc. logo is a trademark of eBay Inc. Used with permission.)

(Image: eBay. The eBay Inc. logo is a trademark of eBay Inc. Used with permission.)

"In this query, one category should not exclude the other," said Fain. Even though such a search might occur only a few times a year, the system takes the long tail into consideration as it comes up with the best matches. From analysis of previous searches, the eBay search engine can connect several words that only infrequently occur together, Fain said.

The search engine has been schooled to carefully judge what category a search belongs in, then check the contents of the category against other clues about what interests the searcher. In the search example above, one clue would be an already brisk business in a popular type of Swiss watch on a leather band.

Fierce Competition

At the end of 2015, Fain said, eBay reported 162 million active buyers. By August 2016, the number had grown to 164 million. The modest increase is significant to a company with flat or declining revenues. The competition is fierce, and customers have other places to go for e-commerce.

The more Fain's team can apply machine learning to ensure customers find what they're searching for, the more likely a search will lead to a sale. It's also more likely prospective buyers will trust the information they're getting.

Machine learning also makes the site more effective at fielding queries coming from foreign buyers, who may be looking at a description of goods in their native language and not necessarily understand the conventions of the originator's language. For example, a search for Burberry handbags with a metal charm has to be handled differently in Spanish than it would be in English.

eBay's machine learning-based translations are making it easier than ever for site visitors who do not speak English to complete purchases. It's important for customers to be able to understand the presentation and value of what's being offered, regardless of where they are in the world or what language they speak.

To that end, Fain said eBay has added a "Best Match" algorithm to the search engine to analyze what's known about the buyer, what's popular among the items being sought, and how particular items might be of value to the prospective buyer. Such matching reflects eBay's "largest-scale application of machine learning," said Fain. "It is a powerful tool for surfacing deals."

For instance, in the sewing machine search example above, a Best Match response might spotlight machines based on value for price. If the searcher is a desktop user, eBay will have space on the screen to display the ranked Best Match results, along with additional categories the visitor might search, such as "antiques" or "collectibles."

On smartphones and other mobile devices there's not enough screen real estate to present much alternative information. That's a problem, because 50% of the business conducted on eBay now involves some form of mobile device, according to Fain. Mobile users get a link to the alternative categories on a new screen if they wish to take another step.

In addition to trying to make the search as relevant as possible, eBay has a big interest in making it reflect marketplace value. Results showing items at a good value for the price are displayed ahead of those with lesser value.

Trustworthiness of a transaction is also a high priority for eBay. Machine learning is applied to discern which factors indicate trustworthiness -- such as the rate of successful completions of sales by a seller -- and which do not. Conversely, if there's a string of complaints or issues with a seller, the result gets knocked down to a lower spot on the list.

By using machine learning, eBay is aiming to make sure both buyer and seller walk away satisfied. As a transaction takes shape, the system is asking, "How likely is it that this transaction will meet our standards?" Fain said. "The results are based on the strength of the evidence, determined by machine learning."

Looking Beyond the Click

Fain compared his five years working at Yahoo -- where the main evidence he had to work with was page clicks -- with the wealth of information available about eBay users.

Clicks tell the system that something has gotten a visitor's attention, but not much else, he said. At eBay, the system can study the click stream that leads to a purchase. "Buying is an incredibly powerful piece of evidence" to feed into a machine learning system, and eBay is in a strong position to collect purchasing evidence and make effective use of it.

Now, eBay engineering is using machine learning to better understand the quality of images used on eBay and to determine what makes effective image quality in a sale. It can employ the powerful parallel processing of graphical processing units in a cluster to analyze visitor interactions with images. "With the dedicated processing of GPUs, we can blast through way more examples," deriving lessons from large, real-world, eBay data sets, said Fain.

While he couldn't cite the number of servers dedicated to machine learning, Fain said they amounted to multiple clusters. EBay has found machine learning a valuable tool and is investing in more machine learning hardware, hiring technical people with machine learning skills, and launching additional machine learning projects. "Machine learning is a big investment for us," he said.

Charles Babcock is an editor-at-large for InformationWeek and author of Management Strategies for the Cloud Revolution, a McGraw-Hill book. He is the former editor-in-chief of Digital News, former software editor of Computerworld and former technology editor of Interactive ... View Full Bio

We welcome your comments on this topic on our social media channels, or [contact us directly] with questions about the site.
Comment  | 
Print  | 
More Insights
Comments
Newest First  |  Oldest First  |  Threaded View
Whoopty
50%
50%
Whoopty,
User Rank: Ninja
9/8/2016 | 7:29:24 AM
Crazy valuations
While I do agree, it does seem to be par for the course that mega corporations don't necessarily make great profits. Uber is a prime example, losing tens of millions of dollars a month and yet it's one of the most highly valued companies in the world.

All it takes is some hype and investment and you don't really need to be worth your valuation. 
PhilipCohen
50%
50%
PhilipCohen,
User Rank: Apprentice
9/7/2016 | 3:02:26 PM
Re: eBay's Machine Learning
Like everything else, shares are worth what someone is prepared to pay for them, and the market says ...

Very recently: EBAY ~$32; PYPL ~$38; AMZN ~$785—LOL ...
melgross
50%
50%
melgross,
User Rank: Ninja
9/7/2016 | 9:23:12 AM
Re: eBay's Machine Learning
Amazon isn't worth that evaluation. It's ridiculous.
PhilipCohen
50%
50%
PhilipCohen,
User Rank: Apprentice
9/6/2016 | 8:38:25 PM
eBay's Machine Learning
LOL ...

"There are a lot of questions out there and I don't have any of the answers,"—eBay CEO Devin Wenig, Goldman Sachs Technology And Internet Conference, 10 Feb. 2016.

2016 Second Quarter Sales: EBAY +3%; AMZN +31%—LOL ...

Fortunately, it's otherwise always been easy to tell when an eBay spokesperson is being disingenuous—their lips are moving ...

And, notwithstanding the constant stream of disingenuous and delusional nonsense that flows from eBay/PayPal, the share price history of these two clunky operators demonstrates the reality:

Aug 2007: (pre John Donahoe) EBAY ~$40; AMZN ~$40;
Jul 2015 (pre eBay-PayPal split): EBAY ~$66; AMZN ~$480;
Jul 2015 (post-split): EBAY ~$28; PYPL ~$37; AMZN ~$530;
Recently: EBAY ~$31; PYPL ~$37; AMZN ~$760—LOL ...

PayPal is still standing still, and eBay has for years been effectively going backwards.

Notwithstanding the "spin-off" of PayPal from eBay, eBay and "PreyPal" remain effectively joined at the hip—for at least the next five years—and anyone that thinks otherwise is simply uninformed; and, thanks to a continuation of most of the destructive policies introduced over the eight year reign (2007–2015) of the "Pain from Bain", John Joseph Donahoe II, the eBay marketplace is continuing on its slow journey down the toilet; nevertheless, during Johnny Ho's occupation of the eBay corner office, this cretin and his gang of hand-picked Keystone Kops still managed to obtain for themselves massive, unearned, "performance" bonuses—while the company's shareholders received not one penny.

PayPal's one-time adoptive parent, eBay, is likely the most unscrupulous commercial entity operating on this planet; but, have no fear, eBay is an equal-opportunity fraudster; demonstrably, they will knowingly aid and abet the defrauding of buyers by unscrupulous eBay merchants who bid on their own auctions, and, conversely, of honest sellers by unscrupulous buyers—as long as there is a financial benefit in such fraud for eBay.

eBay's auction format has been atrophying ever since 2008 when the cretinous Johnny Ho further anonymized bidder IDs to better hide, and further aid and abet, demonstrably rampant shill bidding fraud on consumers by unscrupulous sellers. As time has passed, fewer and fewer people remain naïve enough to still believe that, contrary to its claims, eBay has ever had any intention of protecting consumers from such rampant auction fraud—from which eBay profits. eBay is not concerned about "fraud" unless it directly impacts eBay; eBay has only ever been interested in their FVF, regardless of whether or not the transaction is a fraudulent one. And, a few years ago, eBay raised their final valuation fee (FVF) to 10%, and also removed the fee tiers that moderated the fee paid on higher value items. And so, eBay as a whole has likewise, and deservedly, continued to atrophy.

In early January eBay invited consumers to auction their unwanted Xmas gifts on eBay. And, if you didn't know what your unwanted gift may be worth, eBay's advice was to start the auction at 99c and watch the fun—as your item likely sold for 99c—always presuming you weren't bidding on the auction yourself (and assuming that you or anyone else was able to find the listing in eBay's manipulated search), in which case you would likely finish up buying it yourself; but that's OK with eBay too; they don't mind whether the sale is real or faux, as long as they get their final valuation fee.

eBay's "sell through" rate is now so abysmally low that in their "Completed Listings", whereas they show "sold" items for 90 days, they now show "unsold" items for only 30 days, and that even after they had earlier stopped indicating unsold items in "red" because it looked like too much blood in the water! Which invites the question, how can you tell when eBay is being disingenuous? Their lips are moving ...

The eBay executive suite—where the incompetent mingle with the disingenuous, the unscrupulous, the malevolent, the outright criminal, and the just plain stupid. ...

For a detailed analysis of the ugly reality of eBay's demonstrable, calculated, facilitation of endemic shill bidding fraud on consumers on its auctions marketplace—Google "Shill Bidding on eBay: Case Study #5"

 
Charlie Babcock
50%
50%
Charlie Babcock,
User Rank: Author
9/6/2016 | 8:36:55 PM
PayPal spin out impacted total revenues
EBay points out that PayPal was spun out of eBay on July 17, 2015, which has had an impact on eBay's year over year revenues. Revenues are growing, it asserts, when the PayPal spinout is taken into consideration..
melgross
50%
50%
melgross,
User Rank: Ninja
9/6/2016 | 9:53:30 AM
Feh!
I've been using eBay since 2002. Many of the "advances" over the years have been worse than the previous way of doing things. Their newest app, for example, which has been out for a year, or so, now, is a big step backwards. It's bad enough they added all of that advertising to the older app, which I still use, but the new one rises to new heights in being less useful than ever before. Let's face it, all of these changes are a Google-like effort to increase advertising, and to entice you to buy things you don't really want. While the older app is generally easier to use than the website, there are still glaring deficiencies that need to be fixed. One major one is that when going to a vendor's store, everything, no matter how many, are presented in what appears to be a random list. None of the store's features, such as a selectable index is available. You just have to scroll and scroll, and hope you can FIND what you're looking for. Since more and more people are using their app, on phones, and particularly on tablets, things like this need to be fixed. The rest of the junk they're doing doesn't often work anyway. One thing IT pros can learn from eBay's "advanced" machine learning, it that it usually doesn't work. It's about on the level of Amazon's. You know, when you buy a power drill, and they offer women's undies as a popular buy for people who bought that drill. Nonsense!
News
IBM Puts Red Hat OpenShift to Work on Sports Data at US Open
Joao-Pierre S. Ruth, Senior Writer,  8/30/2019
Slideshows
IT Careers: 10 Places to Look for Great Developers
Cynthia Harvey, Freelance Journalist, InformationWeek,  9/4/2019
Commentary
Cloud 2.0: A New Era for Public Cloud
Crystal Bedell, Technology Writer,  9/1/2019
White Papers
Register for InformationWeek Newsletters
Video
Current Issue
Data Science and AI in the Fast Lane
This IT Trend Report will help you gain insight into how quickly and dramatically data science is influencing how enterprises are managed and where they will derive business success. Read the report today!
Slideshows
Flash Poll