Connect with us

Tech

BEAST-GB model combines machine learning and behavioral science to predict people’s decisions

Published

on

BEAST-GB model combines machine learning and behavioral science to predict people’s decisions


Illustration of the model BEAST-GB. Credit: Plonsky et al.

A key objective of behavioral science research is to better understand how people make decisions in situations where outcomes are unknown or uncertain, which entail a certain degree of risk.

The ability to predict people’s choices in these situations could be highly advantageous, as it could help to draft effective initiatives aimed at prompting people to make better decisions for themselves and others in their community.

Researchers at Technion (Israel Institute of Technology) and various institutes in the United States recently developed a new computational model called BEAST-GB, which was found to predict people’s decisions in situations that entail risk and uncertainty.

Their proposed model, outlined in a paper published in Nature Human Behavior, combines advanced machine learning algorithms with behavioral science theory.

“Human-decision research is rich in competing theories, yet none reliably and accurately predicts human choices across contexts,” Ori Plonsky, first author of the paper, told Tech Xplore.

“To see which ideas really work, we organized CPC18, a ‘choice prediction competition’ in which anyone could submit a to predict people’s decisions under risk and uncertainty. We were especially interested in knowing if data-driven machine learning, theory-driven behavioral models, or, as was our guess, a hybrid that embeds behavioral theory inside ML, would excel.”

The new machine learning model developed by Plonsky and his colleagues draws from a behavioral science framework known as BEAST (Best Estimate and Sampling Tools). This is a model based on psychological theories that were previously found to predict people’s decisions with good accuracy.

“BEAST assumes that, in choice under risk and uncertainty, people mix several strategies, such as minimizing the chances of immediate regret or hedging against worst outcomes,” explained Plonsky.

“We translated each strategy into a ‘behavioral feature,’ a concise formula that captures how sensitive a decision-maker should be to that consideration in any given choice task. We then fed these theory-based features, plus purely objective task descriptors, into Extreme Gradient Boosting (a machine learning algorithm known to be highly useful in prediction tournaments)—hence the name BEAST-GB.”

With the enhancements implemented by the researchers, the BEAST-GB model could analyze behavioral data and derive the motives driving decisions, as well as the impact of these motives in different decision-making scenarios.

Notably, BEAST-GB won the CPC18 Choice Prediction Competition in 2018, capturing 93% of predictable variation in the data it was fed, and 96% in follow-up tests utilizing a dataset that was 40 times larger.

“BEAST-GB outperformed dozens of mainstream behavioral models and purely data-driven machine learning,” said Plonsky.

“With just 2% of the training data, it has already beat a deep neural network trained on all the . The model even accurately predicts choices people make in new experiments it has never seen, implying it captures general human choice patterns. Finally, we used it to improve and enhance the underlying interpretable behavioral theory, so it enhances our ability to explain, not only predict, human decision making.”

This recent work highlights the promise of machine learning models that also draw from behavioral science for predicting people’s decisions and responses in real-world scenarios. In the future, BEAST-GB and other similar models could guide the design of new large-scale interventions aimed at improving people’s decisions via nudges, incentives or other behavioral science-based strategies.

Plonsky and his colleagues eventually plan to collaborate with policymakers and other parties involved in the design or implementation of behavioral science initiatives. This would allow them to test their model “in the wild,” validating its potential in real-world settings, while also yielding insight that could inform its further advancement.

“Other recent publications have suggested that human decision-making and other behaviors can be very effectively predicted using advanced data-driven machine learning methods like large language models tuned on large behavioral data,” added Plonsky.

“We now plan to continue investigating when and how BEAST-like theory can enhance such data-driven methods in predicting behavior. Specifically, we plan to extend our domain of research by including natural-language decision problems, more aligned with the real world.”

Written for you by our author Ingrid Fadelli,
edited by Sadie Harley, and fact-checked and reviewed by Robert Egan—this article is the result of careful human work. We rely on readers like you to keep independent science journalism alive.
If this reporting matters to you,
please consider a donation (especially monthly).
You’ll get an ad-free account as a thank-you.

More information:
Ori Plonsky et al, Predicting human decisions with behavioural theories and machine learning, Nature Human Behaviour (2025). DOI: 10.1038/s41562-025-02267-6.

© 2025 Science X Network

Citation:
BEAST-GB model combines machine learning and behavioral science to predict people’s decisions (2025, August 14)
retrieved 14 August 2025
from https://techxplore.com/news/2025-08-beast-gb-combines-machine-behavioral.html

This document is subject to copyright. Apart from any fair dealing for the purpose of private study or research, no
part may be reproduced without the written permission. The content is provided for information purposes only.





Source link

Tech

Apple’s Price-Friendly iPhone 17e Gets a MagSafe Upgrade

Published

on

Apple’s Price-Friendly iPhone 17e Gets a MagSafe Upgrade


Apple’s first hardware launch of 2026—not counting the second-generation AirTag it debuted at the end of January—is the next iteration of the price-friendly iPhone: the iPhone 17e. The company announced the handset via an online press release, ahead of its “Special Apple Experience” in New York City this Wednesday.

While last year’s iPhone 16e was widely criticized for its questionable value—it replaced the iPhone “SE” models from yesteryear and jacked the price up from $429 to $599—the newer model in the series has some notable features that were missing in its predecessor, like Apple’s MagSafe technology and the Dynamic Island. The price remains firm at $599 despite the challenging economic environment and the memory shortage.

The iPhone 17e opens for preorder today and will be widely available on March 11.

E for Effort

Apple has stuck with the same 6.1-inch OLED display as the iPhone 16e, down to the same old-school notch design. That means you won’t get the sleek look of the Dynamic Island, which also doubles as a live notifications display. Thankfully, if you’re worried about durability, this iPhone has the same Ceramic Shield 2 front glass protecting the display as its pricier siblings, giving it a nice strength boost from the previous generation.

Apple did not upgrade the screen with its ProMotion refresh rate tech, as it’s stuck at 60 Hz. This capability is the number of times the screen refreshes with images—the higher the better, as your display will appear smoother, with interactions feeling more fluid. It’s something the company has offered in the iPhone Pro models, and finally enabled in 2025 with its entire iPhone 17 range, but you’ll have to upgrade for the luxury. It’s a shame, as most budget Android phones offer 120 Hz as standard, even devices as cheap as $200. That also means the iPhone 17e doesn’t have the option to enable an always-on display.

Arguably, the best upgrade is the addition of MagSafe, the magnetic ring that has been embedded in the back of mainline iPhones since the iPhone 12. Apple confusingly didn’t include it with the iPhone 16e despite a healthy accessory market that would have made the iPhone 16e a little more versatile. While the 16e still had basic wireless charging, with the iPhone 17e, you can take advantage of faster magnetic wireless charging at 15 watts (plus access to MagSafe accessories).

This iPhone is powered by the A19 chipset, which debuted on the iPhone 17, though there’s one less graphics core, so graphics performance is a small step below. That’s in line with what Apple did with the iPhone 16e and the iPhone 16 that came before. Apple didn’t share RAM details yet, but it’s likely that the iPhone 17e has 8 GB of RAM like its predecessor, whereas the rest of the iPhone 17 lineup has 12 GB.

Courtesy of Apple



Source link

Continue Reading

Tech

A Former Top Trump Official Is Going After Prediction Markets

Published

on

A Former Top Trump Official Is Going After Prediction Markets


Mick Mulvaney wants to be clear: He really likes gambling. “You’re talking to the only former member of Congress who’s won a poker tournament in Las Vegas,” he tells WIRED. When he was representing South Carolina in the US House of Representatives, he pushed for the state to allow sports betting.

Because of his background, Mulvaney, a former Trump administration official, says he can tell when something is gambling—and that the sports contracts on prediction markets fit the bill. “You know the old saying, if it walks like a duck and quacks like a duck, it’s a duck?” he asks. “If it looks like a sports bet, if it sounds like a sports bet, if it pays off like a sports bet, if it’s on a sporting event—it’s a sports bet.”

Mulvaney, who was President Trump’s acting White House chief of staff from 2019 to 2020, is now leading a new advocacy coalition called Gambling Is Not Investing, which will lobby for prediction markets to be regulated by state gambling laws. He joins a number of other prominent Republicans calling for similar rules. Earlier this month, former New Jersey Governor Chris Christie and current Utah Governor Spencer Cox both spoke out against the current federal approach to regulating prediction markets. (Christie also used the “quack like a duck” line.)

These developments are part of a fierce political battle over how prediction markets are regulated. On the federal level, the Commodity Futures Trading Commission (CFTC) oversees these platforms, which are currently classified as derivatives markets. While a traditional sportsbook will offer customers a chance to place a bet on which team will win or lose a game, a prediction market will offer an “event contract” on the outcome. Critics view the difference as little more than a loophole, and state authorities from across the country are currently pursuing lawsuits against prediction market companies like Kalshi, alleging that they violate state gambling laws. (While these markets offer event contracts on a wide variety of topics, sporting events are their most popular offerings.) “I love the CFTC, but they’re not set up to do this,” says Mulvaney.

Recently, a group of 23 Democratic Senators sent the CFTC a letter urging it to allow these court cases to play out. It did not appear to go over well; CFTC head Michael Selig insists that prediction markets are correctly classified, and that his agency has jurisdiction over the industry. After Selig released a video promising to see those who “challenge our authority” in court, the CFTC even took the unprecedented step of filing a brief in support of the cryptocurrency platform Crypto.com, which faces a lawsuit from Nevada regulators over its prediction market offering.

During the Biden Administration, the CFTC took a notably different approach to prediction markets, even fining Polymarket $1.4 million for failing to register as a derivatives market and temporarily blocking it from operating in the US.

Now, though, the agency’s friendlier approach appears to dovetail with the White House’s interest in the industry. The Trumps have numerous ties to the prediction market world. Truth Social, the social media platform majority-owned by President Trump and his family, is planning its own prediction market offering, reportedly called Truth Predict. Donald Trump Jr is an advisor to both Kalshi and Polymarket, and his venture capital firm has invested in the latter.

But the launch of Gambling Not Investing demonstrates that there is a growing wing of the Republican party that feels the prediction markets need more guardrails. Its founding member organizations include a number of conservative consumer advocacy groups, including Moms for America, Consumer Action for a Strong Economy, and Frontiers of Freedom.

Mulvaney is hopeful that he can make his case to the current White House. “Their default position is going to be to regulate less, not more. And I respect that,” he says. “But I also know that in the first Trump administration, when there were common sense reasons to do some regulation, that we did that.”



Source link

Continue Reading

Tech

When the Internet Goes Dark, the Truth Goes With It

Published

on

When the Internet Goes Dark, the Truth Goes With It


Alaqad says that because traditional media outlets pick and choose what to show their audiences, losing on-the-ground journalists means losing parts of the truth. “When the people are being silenced and censored, and they don’t have a space for them to talk or a platform to express what’s happening, and for us to see what’s happening through their eyes, there will always be limitations [on] how much we know,” she says.

In every crisis, when communication breaks down, accountability is lost and injustice becomes easier to ignore. “Injustice is super loud,” Alaqad says. “Justice needs to be louder.”

Targeted

Journalists are also silenced permanently. Reporters Without Borders (RSF) wrote in December 2025 that 67 media professionals were killed that year, 43 percent of whom were killed in Gaza by Israeli armed forces. The total number of journalists killed in Gaza since October 7, 2023 has risen to over 220, according to the RSF. The UN estimate sits at more than 260.

“When we look at it within the framework of imposing a ban on the foreign press entering Gaza now, more than two years into that war, when they are restricting the free movement of journalists within Gaza and into Gaza, when we are talking about an unprecedented massacre of journalists, the targeting of media offices and the targeting of communication infrastructure just becomes another piece of that puzzle, which aims at imposing a media blackout,” Dagher says. Israel has repeatedly denied claims that it targets journalists or media infrastructure.

“Killing journalists means killing and silencing the truth,” Alaqad says. In her experience, this strategy works on multiple levels—killing journalists means fewer people reporting on the ground, but equally, it turns journalists into a threat to the people. “This is also sending a message to the people that all journalists are a threat, don’t talk to journalists, stay away from journalists,” she explains.

She recalls her mother begging her not to wear her press vest and helmet. Meant to signify neutrality and protect journalists in the field, instead, it made her feel like a target. “It’s supposed to protect, but on the contrary, it actually puts risk on your life and even on your beloved ones and the ones around you,” she explains.

Alaqad says it was not always this way. Early on, people would greet journalists, offer them food, and thank them for their work. “After a couple of months, when they’d seen journalists getting targeted, Palestinians started treating journalists differently,” she says.

To report in Gaza was to work inside a landscape where time itself was unstable and not guaranteed. Plans rarely extended beyond daylight. Conversations ended abruptly. Addresses became memorials overnight. “The only certainty in Gaza is uncertainty,” Alaqad says.

She recalls interviewing families and planning to return the next day, only to find that the people she spoke with had been killed in airstrikes.

She has since left Gaza, and is pursuing a master’s degree in media studies at the American University of Beirut. She received the Shireen Abu Akleh Memorial Endowed Scholarship, named for the Palestinian journalist killed by Israeli forces in May 2022.

Digital Truths

Going viral on social media helped her reach people, but it also put her at risk. “It showed millions of people around the world what’s happening in Gaza, but at what cost? Being in Gaza could cost you your life, especially as a journalist,” she says.

Despite the reach of digital reporting, she does not trust its permanence. Accounts disappear, posts are removed and videos are lost. What is available today may be gone tomorrow.



Source link

Continue Reading

Trending