Happy Friday. This newsletter is coming to you from the distant past (read: two days ago). The Emerging Tech Brew crew is enjoying a day off, possibly—no promises, though—doing something other than thinking about tech.
In today’s edition:
🛍 AI–powered e-commerce Best of the Brew Weekend reads
—Hayden Field, Dan McCarthy
|
|
Francis Scialabba
Whether you’re typing “PlayStation 5,” “Dyson Airwrap,” or “Taylor Swift on vinyl” into a retailer’s search bar, algorithms help make holiday-shopping wishlists a reality.
Using machine learning, natural language processing, and purchase data, an algorithm can connect your query to the results and, for better or for worse, also decide more products to recommend.
-
This behind-the-scenes tech helps fuel the $4.2 trillion global industry that is online shopping.
For Black Friday, Emerging Tech Brew talked with Nilay Oza, CEO and cofounder of Klevu—a Finnish tech company that fuels smart search for 3,000+ brands, including Puma, Avon, and ColourPop. Klevu was founded in 2013 and has raised ~$18 million to date.
Inside the algorithm
The company’s algorithm has a few different components to it, but it all starts with linguistics.
First up: offline processing. Once Klevu gets access to a store’s catalog, it uses natural language processing to add richer, fuller descriptions of each product for the machine’s benefit. That means adding linguistically relevant synonyms or annotations (think: adding “outdoor furniture” or “oak wood” to the description of a garden bench).
- For instance, if you’ve got your heart set on a new pair of combat boots, for the best chance of relevant search results, that item would also need to be tagged with keywords like “shoes,” “leather,” “zip-up,” and the like.
Eventually, the catalog expands by 2x–3x, Oza said, all thanks to natural language processing, strategic synonyms, and annotations.
Next up: query processing. Say you’ve got a budget for that pair of combat boots, and you’re searching for a pair either around $100 or under $100—two very different searches.
- “As humans, it is very easy for us to understand that the intent is different—how do you make software understand?” Oza told us. “That’s what we do.”
Part of it comes down to language rules that a machine can analyze and use as go-to shortcuts—like the fact that in the English language, if there are two nouns in a row, the second one is typically the “primary subject,” Oza said.
- Exhibit A: If you’re looking for a waist belt to go with your combat boots, it’s a lot more likely you’re primarily looking for a belt, not a waist.
Where does ML come in?
Primarily after you press Enter on your search. Either you click on the combat boots, exit the site, or start searching something else—and, sort of like Big Brother, the ML algorithm is watching.
Oza told us Klevu keeps data store-specific (even if two retailers are owned by the same parent company). It typically tracks a shopper’s IP address—and “nothing else,” Oza said—from session to session, and notes what they view, click on, and purchase. That information then influences the products recommended to others with similar behavior.
- Since the algorithm’s training data comes from user behavior, and it’s store-specific, it typically takes about 30 days for the algorithm to learn enough to make the best possible recommendations.
- The company also asks retailers for historic sales data to arm the algorithm with some info in getting started, Oza explained.
And it all comes back to natural language processing in the end—if you search a less-common term and then click on a product, the term you used will be added to the catalog to help make future results more relevant to others.
Bottom line: What you search for, click on, and buy today are making our algorithmic overlords ever-smarter—and, in theory, better at selling you stuff. So watch your wallet.
Click here to view this story on-site.—HF
|
|
Francis Scialabba
There’s only one Morning Brew publication devoted to emerging technologies (hint: you’re reading it), but that doesn’t mean we’re the only Morning Brew pub to ever write about tech.
Here are some of our favorite recent tech stories from the other Morning Brew publications:
-
An explainer on clean rooms, a buzzy, privacy-centric ad-tech tool that aims to enable data-sharing while protecting consumer privacy. (Marketing Brew)
-
The EEOC is cracking down on the use of AI in hiring. (HR Brew)
-
Data- and AI-driven personalization is now table stakes for retailers. (Retail Brew)
-
The weight of being a whistleblower in tech. (Morning Brew)
-
Breaking down climate tech. (Business Casual)
Bonus round: Oh, and don’t miss our recent collaboration with Retail Brew—it’s all about virtual fitting rooms.
|
|
Gift guides for the guy in your life often suggest one of three categories: grill, drill, or tie (womp womp). This year, consider going the comfy route.
And no, we’re not talkin’ run-of-the-mill kind of comfy. We’re talking about Lahgo’s luxurious sleepwear, like their Button-Up Short Set and Button-Up Long Set made with their bestselling washable silk. That’s silky, machine-washable goodness. Ahem.
Is it hot in here? No, because this sleepwear is also thermoregulating.
Lahgo’s sets are ideal for lounging, too—something his tie collection could never pull off.
And right now, Lahgo will even gift you their Cotton Terry Shaving Towel (while supplies last) if you spend over $200 with them until Nov. 29.
And, until Dec. 20, you can also save $20 on your first order of $100+ with code FOR-MORNINGBREW.
Shop here.
|
|
Giphy
We just gave you the best of the Brew as it relates to emerging tech stories, now here’s the best of the rest:
|
|
Where it all h(app)ens: With the Dialpad app, you can talk, message, and meet with your teams, all in one glorious space. Join companies like Uber, WeWork, and more in letting your teams work and communicate from anywhere, on any device, with Dialpad. No long-term contracts. No pesky hidden fees. Start with a 14-day free trial here.
|
|
Francis Scialabba
Stat: By the end of 2030, energy-storage plants will support over 1 terawatt-hour of energy, a massive increase from just 34 gigawatt-hours at the end of 2020. Getting there will require ~$262 billion in investment.
Quote: “If JPM doesn’t withdraw their lawsuit, I will give them a one star review on Yelp. This is my final warning!”—Elon Musk to The Wall Street Journal, re: the reported feud between him and JPMorgan CEO Jamie Dimon
Read: Why an ancient mammoth tusk was found 10,000 feet under the sea.
Video skillz: With Vimeo’s powerful video tools, you can create, edit, share, and stream your content, all from one platform. Customize quality content, and get it all for 25% off—but only until 11/30/21.*
*This is sponsored advertising content
|
|
Wiggle Worm. Happy Dragon. Dachshund.
These are the names of just three of the 10 exclusive Macy’s Thanksgiving Day Parade NFTs the company is auctioning off this week. No, we have not hit peak crypto, why do you ask?
- As of Wednesday, when we hit Send on this newsletter, the NFTs had an average bid of $5,250, with the highest being $7,000 for the 1920’s toy soldier NFT.
- Proceeds from the 10 auctions will benefit Make-A-Wish.
|
|
Three of the following news stories are true, and one...we made up. Can you spot the odd one out?
-
El Salvador plans to build a “Bitcoin City,” and offer $1 billion in “bitcoin bonds.”
-
Adele sparked a major UX change at Spotify.
-
Rolls-Royce claims it has made the world’s fastest electric plane.
-
A cultivated-turkey-meat startup promises lab-grown turkey that is juicier and tryptophan-free, by next Thanksgiving.
|
|
Catch up on the top Emerging Tech Brew stories from the past few editions:
|
|
We have not heard of any turkey-focused lab-grown meat company making such promises.
|
|
Written by
Hayden Field and Dan McCarthy
Was this email forwarded to you? Sign up
here.
|
ADVERTISE
//
CAREERS
//
SHOP
//
FAQ
Update your email preferences or unsubscribe
here.
View our privacy policy
here.
Copyright ©
2021
Morning Brew. All rights reserved.
22 W 19th St, 8th Floor, New York, NY 10011
|
|