Daily Archives: August 24, 2023

The predictive power of social media data in fashion forecasting

Posted on by

Fashion and social media are both ever evolving. So why not put the two together? New research in Manufacturing & Service Operations Management says utilizing social media to predict sales of apparel and footwear items based on social media posts and interactions about color is possible and successful.

“We partner with three multinational retailers—two apparel and one footwear—and combine their data sets with publicly available data on Twitter and the Google Search Volume Index. We implement a variety of models to develop forecasts that can be used in setting the initial shipment quantity for an item, arguably the most important decision for fashion retailers,” says Youran Fu of Amazon, one of the study authors.

Despite challenges like short product lifetimes, long manufacturing lead times and constant innovation of fashion products, information can enable efficiency and increased revenue.

“Our findings show that fine-grained social media information has significant predictive power in forecasting color and fit demands months in advance of the sales season, and therefore greatly helps in making the initial shipment quantity decision,” says Marshall Fisher of the University of Pennsylvania.

“The predictive power of including social media features, measured by the improvement of the out-of-sample mean absolute deviation over current practice, ranges from 24% to 57%,” Fisher continues.

The paper, “The Value of Social Media Data in Fashion Forecasting,” proves consistent results across all three retailers. The researchers demonstrate the robustness of the findings over market and geographic heterogeneity, and different forecast horizons.

The researchers note, “Changes in fashion demand are driven more by ‘bottom-up’ changes in consumer preferences than by ‘top-down’ influence from the .”

More information: Youran Fu et al, The Value of Social Media Data in Fashion Forecasting, Manufacturing & Service Operations Management (2023). DOI: 10.1287/msom.2023.1193

Source: The predictive power of social media data in fashion forecasting

Paralysed woman able to ‘speak’ through digital avatar

Posted on by

 

A severely paralysed woman has been able to speak through an avatar using technology that translated her brain signals into speech and facial expressions.

[…]

The latest technology uses tiny electrodes implanted on the surface of the brain to detect electrical activity in the part of the brain that controls speech and face movements. These signals are translated directly into a digital avatar’s speech and facial expressions including smiling, frowning or surprise.

[…]

The patient, a 47-year-old woman, Ann, has been severely paralysed since suffering a brainstem stroke more than 18 years ago. She cannot speak or type and normally communicates using movement-tracking technology that allows her to slowly select letters at up to 14 words a minute. She hopes the avatar technology could enable her to work as a counsellor in future.

The team implanted a paper-thin rectangle of 253 electrodes on to the surface of Ann’s brain over a region critical for speech. The electrodes intercepted the brain signals that, if not for the stroke, would have controlled muscles in her tongue, jaw, larynx and face.

After implantation, Ann worked with the team to train the system’s AI algorithm to detect her unique brain signals for various speech sounds by repeating different phrases repeatedly.

The computer learned 39 distinctive sounds and a Chat GPT-style language model was used to translate the signals into intelligible sentences. This was then used to control an avatar with a voice personalised to sound like Ann’s voice before the injury, based on a recording of her speaking at her wedding.

The technology was not perfect, decoding words incorrectly 28% of the time in a test run involving more than 500 phrases, and it generated brain-to-text at a rate of 78 words a minute, compared with the 110-150 words typically spoken in natural conversation.

[…]

Prof Nick Ramsey, a neuroscientist at the University of Utrecht in the Netherlands, who was not involved in the research, said: “This is quite a jump from previous results. We’re at a tipping point.”

A crucial next step is to create a wireless version of the BCI that could be implanted beneath the skull.

[…]

Source: Paralysed woman able to ‘speak’ through digital avatar in world first | Neuroscience | The Guardian

Tornado Cash ‘laundered over $1B’ in criminal cryptocurrency

Posted on by

Two founders of Tornado Cash were formally accused by US prosecutors today of laundering more than $1 billion in criminal proceeds through their cryptocurrency mixer.

As well as unsealing an indictment against the pair on Wednesday, the Feds also arrested one of them, 34-year-old Roman Storm, in his home state of Washington, and hauled him into court. Fellow founder and co-defendant Roman Semenov, a 35-year-old Russian citizen, is still at large.

As a cryptocurrency mixer, Tornado Cash is appealing to cybercriminals as it offers to provide them a degree of anonymity.

[…]

Tornado Cash was sanctioned by Uncle Sam a little over a year ago for helping North Korea’s Lazarus Group scrub funds stolen in the Axie Infinity hack. Additionally, the US Treasury Department said Tornado Cash was used to launder funds stolen in the Nomad bridge and Harmony bridge heists, both of which were also linked to Lazarus.

Storm and Semenov were both charged with conspiracy to commit money laundering and conspiracy to commit sanctions violations, each carrying a maximum penalty of 20 years in prison. A third charge, conspiracy to operate an unlicensed money transmitting business, could net the pair up to an additional five years upon conviction.

In the unsealed indictment [PDF], prosecutors said Tornado Cash boasted about its anonymizing features and that it could make money untraceable, and that Storm and Semenov refused to implement changes that would dial back Tornado’s thief-friendly money-laundering capabilities and bring it in line with financial regulations.

“Tornado Cash failed to establish an effective [anti money laundering] program or engage in any [know your customer] efforts,” Dept of Justice lawyers argued. Changes made publicly to make it appear as if Tornado Cash was legally compliant, the DoJ said, were laughed off as ineffective in private messages by the charged pair.

“While publicly claiming to offer a technically sophisticated privacy service, Storm and Semenov in fact knew that they were helping hackers and fraudsters conceal the fruits of their crimes,” said US Attorney Damian Williams. “Today’s indictment is a reminder that money laundering through cryptocurrency transactions violates the law, and those who engage in such laundering will face prosecution.”

What of the mysterious third founder?

While Storm and Semenov were the ones named on the rap sheet, they aren’t the only people involved with, or arrested over, their involvement in Tornado Cash. A third unnamed and uncharged person mentioned in the DoJ indictment referred to as “CC-1” is described as one of the three main people behind the sanctioned service.

Despite that, the Dept of Justice didn’t announce any charges against CC-1.

Clues point to CC-1 potentially being Alexey Persev, a Russian software developer linked to Tornado Cash who was arrested in The Netherlands shortly after the US sanctioned the crypto-mixing site. Persev was charged in that Euro nation with facilitating money laundering and concealing criminal financial flows, and is now out of jail on monitored home release awaiting trial.

Persev denies any wrongdoing, and claimed he wasn’t told why he was being detained. His defenders argued he shouldn’t be held accountable for writing Tornado Cash code since he didn’t do any of the alleged money laundering himself.

It’s not immediately clear if Pertsev is CC-1, nor is it clear why CC-1 wasn’t charged. We put those questions to the DoJ, and haven’t heard back.

Source: Tornado Cash ‘laundered over $1B’ in criminal cryptocurrency