TIMES.KY

Cayman Islands, Caribbeanand International News
Thursday, Mar 28, 2024

Experts dissected TikTok's algorithm and say a US buyer will struggle to replicate its magic

Anyone who buys TikTok will struggle to replicate the app's magic if the purchase doesn't include its recommendation algorithm, experts say.
Technology experts told Business Insider that TikTok's recommendation algorithm was stronger than those of rivals partly because the company had access to extensive training data. TikTok is thought to be wrangling over whether it can sell its recommendation algorithms to a US buyer as part of a wider deal, thanks to new Chinese rules. "I think you can still replicate a lot of the magic of the algorithm if they were going to give you all the user data and all the video data, but you'd have to be willing to support that entire process," said Eugene Wei, a product expert who wrote a popular blog post analyzing the algorithm.

Any company that buys TikTok may struggle to replicate the video app's magic if it buys the service without its recommendation algorithms, experts tell Business Insider.

The app's parent company, ByteDance, is in negotiations with bidders over the sale of TikTok's US business after President Donald Trump in August threatened to ban the app without a sale. Lead bidders for a deal - perhaps worth as much as $30 billion - include Microsoft, in partnership with Walmart, and Oracle.

But discussions have been slowed by new Chinese rules restricting the export of key services, including algorithms. The upshot is that a US buyer may end up buying TikTok's US arm but only licensing the recommendation algorithm that makes the app so compelling.

"I personally think TikTok wouldn't be TikTok without its algorithm," said Bondy Valdovinos Kaye, a researcher at Queensland University of Technology, who has investigated TikTok.


Employees call TikTok's algorithm its crown jewel


TikTok has charmed about 100 million users in the US, and superficially it isn't that different from YouTube. People upload short videos of themselves doing anything from participating in set challenges to posting comedy skits and memes.

What differentiates the app is its "For You" page, which throws up a beguiling mix of highly shareable short videos. Like YouTube and apps like Netflix, this centers on a system that recommends what users should watch next. What's uncanny about TikTok is how good it is at it.

Valdovinos Kaye visited ByteDance's Beijing offices in 2019, where employees called the algorithm the "crown jewel" of ByteDance's success.

The algorithm was developed as a collaboration between ByteDance's AI Lab and Peking University, Valdovinos Kaye said, and is the secret sauce that powers all ByteDance's software.

Initially developed for Toutiao, ByteDance's news aggregator, it is now used in every version of ByteDance's apps, including Douyin, the Chinese version of TikTok.

"We're yet to see anyone else really successfully master recommendation to the degree they have," said Sabba Keynejad of Veed, a video-editing app that has attempted to reverse engineer the algorithm.

Certainly, ByteDance employs a vast engineering workforce to develop the algorithm.

When Valdovinos Kaye visited the Beijing offices, he was confronted with a multistory office packed with programmers. (TikTok declined an interview request for this story. It did, however, publish a blog post in June providing a high-level explanation of the workings of its algorithm.)


It's more than just the algorithm


Keynejad added that we might be bestowing the algorithm with more influence than it has.

"The algorithm isn't the thing that runs everything, but I think it's a perfect storm," he said. "It's product meets the right time in the market, meets these unengaged teens with this great recommendation engine, and all these themes running through the app."

That's something Eugene Wei, a former product chief at companies including Flipboard and Amazon, agrees with. Wei previously delved into the magic behind TikTok's algorithms in a popular blog post.

"It has really easy-to-use video filters and editing tools combined with an algorithm that puts it in front of a lot of people quickly and gets feedback," he said. "That whole flywheel is connected at every point."

He added: "A lot of people are treating the algorithm by itself as some sort of black magic.

"I don't think it's actually that. Most people who build recommendation engines using machine learning say it's pretty likely the techniques they use are pretty standard."

Nikita Aggarwal of the Oxford Internet Institute added that the algorithm learned from the huge amounts of data that TikTok could draw from.

"It collects potentially more user data from other apps, and so is able to better profile the user and therefore recommend what videos they are more likely to enjoy," she said. She also agrees that the app's design - and its focus on full-screen immersive video - helps improve its popularity.

"Every click reveals a user's preference, to the extent that this gives TikTok more useful information about a user's preference and understanding that is what makes an app big," she says.

The app can also test a user's interests at a scale unimaginable for other platforms such as YouTube.

The short format of TikTok videos - none longer than a minute - means users can rifle through them at a far faster rate than on YouTube, where the average video can be longer than 12 minutes.

"It's harder to do for YouTube because they don't necessarily have an app that is putting a lot of random videos in front of a lot of people," Wei said. "People kind of self-select what they watch on YouTube, which is fine."

TikTok's For You page serves its users hundreds of videos an hour, meaning it can occasionally try videos it's not certain users will like with little effect.

"The feedback only takes a few seconds for me to register how I feel about a video, and because it's full screen, the app can assume that whatever I do reflects my opinion on that video," Wei said.

That real-life data used to hone TikTok's machine-learning algorithm is in turn more powerful than the training data sets other services use.


A buyer will struggle to replicate the algorithm's power


Even if it's a relatively standard algorithm, TikTok's has been well-trained on its nearly 600 million monthly active users — which could prove problematic if the algorithm isn't transferred over through a sale.

"I think you can still replicate a lot of the magic of the algorithm if they were going to give you all the user data and all the video data, but you'd have to be willing to support that entire process," Wei said.

"One of the things that comes up in this context is how you associate the values of the algorithmic system or the algorithm and the data it's trained on," Aggarwal added.

"If it was sold to Microsoft, Microsoft presumably could benefit from the same data, but there are the insights that ByteDance has already acquired from users it's already had or exposed the machine learning algorithm to, and that is valuable.

"The historical training has legacy value, which clearly China recognizes."

Newsletter

Related Articles

TIMES.KY
0:00
0:00
Close
Paper straws found to contain long-lasting and potentially toxic chemicals - study
FTX's Bankman-Fried headed for jail after judge revokes bail
Blackrock gets half a trillion dollar deal to rebuild Ukraine
Israel: Unprecedented Civil Disobedience Looms as IDF Reservists Protest Judiciary Reform
America's First New Nuclear Reactor in Nearly Seven Years Begins Operations
Southeast Asia moves closer to economic unity with new regional payments system
Today Hunter Biden’s best friend and business associate, Devon Archer, testified that Joe Biden met in Georgetown with Russian Moscow Mayor's Wife Yelena Baturina who later paid Hunter Biden $3.5 million in so called “consulting fees”
Singapore Carries Out First Execution of a Woman in Two Decades Amid Capital Punishment Debate
Google testing journalism AI. We are doing it already 2 years, and without Google biased propoganda and manipulated censorship
Unlike illegal imigrants coming by boats - US Citizens Will Need Visa To Travel To Europe in 2024
Musk announces Twitter name and logo change to X.com
The politician and the journalist lost control and started fighting on live broadcast.
The future of sports
Unveiling the Black Hole: The Mysterious Fate of EU's Aid to Ukraine
Farewell to a Music Titan: Tony Bennett, Renowned Jazz and Pop Vocalist, Passes Away at 96
Alarming Behavior Among Florida's Sharks Raises Concerns Over Possible Cocaine Exposure
Transgender Exclusion in Miss Italy Stirs Controversy Amidst Changing Global Beauty Pageant Landscape
Joe Biden admitted, in his own words, that he delivered what he promised in exchange for the $10 million bribe he received from the Ukraine Oil Company.
TikTok Takes On Spotify And Apple, Launches Own Music Service
Global Trend: Using Anti-Fake News Laws as Censorship Tools - A Deep Dive into Tunisia's Scenario
Arresting Putin During South African Visit Would Equate to War Declaration, Asserts President Ramaphosa
Hacktivist Collective Anonymous Launches 'Project Disclosure' to Unearth Information on UFOs and ETIs
Typo sends millions of US military emails to Russian ally Mali
Server Arrested For Theft After Refusing To Pay A Table's $100 Restaurant Bill When They Dined & Dashed
The Changing Face of Europe: How Mass Migration is Reshaping the Political Landscape
China Urges EU to Clarify Strategic Partnership Amid Trade Tensions
Europe is boiling: Extreme Weather Conditions Prevail Across the Continent
The Last Pour: Anchor Brewing, America's Pioneer Craft Brewer, Closes After 127 Years
Democracy not: EU's Digital Commissioner Considers Shutting Down Social Media Platforms Amid Social Unrest
Sarah Silverman and Renowned Authors Lodge Copyright Infringement Case Against OpenAI and Meta
Italian Court's Controversial Ruling on Sexual Harassment Ignites Uproar
Why Do Tech Executives Support Kennedy Jr.?
The New York Times Announces Closure of its Sports Section in Favor of The Athletic
BBC Anchor Huw Edwards Hospitalized Amid Child Sex Abuse Allegations, Family Confirms
Florida Attorney General requests Meta CEO's testimony on company's platforms' alleged facilitation of illicit activities
The Distorted Mirror of actual approval ratings: Examining the True Threat to Democracy Beyond the Persona of Putin
40,000 child slaves in Congo are forced to work in cobalt mines so we can drive electric cars.
BBC Personalities Rebuke Accusations Amidst Scandal Involving Teen Exploitation
A Swift Disappointment: Why Is Taylor Swift Bypassing Canada on Her Global Tour?
Historic Moment: Edgars Rinkevics, EU's First Openly Gay Head of State, Takes Office as Latvia's President
Bye bye democracy, human rights, freedom: French Cops Can Now Secretly Activate Phone Cameras, Microphones And GPS To Spy On Citizens
The Poor Man With Money, Mark Zuckerberg, Unveils Twitter Replica with Heavy-Handed Censorship: A New Low in Innovation?
Unilever Plummets in a $2.5 Billion Free Fall, to begin with: A Reckoning for Misuse of Corporate Power Against National Interest
Beyond the Blame Game: The Need for Nuanced Perspectives on America's Complex Reality
Twitter Targets Meta: A Tangle of Trade Secrets and Copycat Culture
The Double-Edged Sword of AI: AI is linked to layoffs in industry that created it
US Sanctions on China's Chip Industry Backfire, Prompting Self-Inflicted Blowback
Meta Copy Twitter with New App, Threads
The New French Revolution
BlackRock Bitcoin ETF Application Refiled, Naming Coinbase as ‘Surveillance-Sharing’ Partner
×