The Owners Of The "shop Without Sellers" Trained AI To Detect Thieves - Alternative View

The Owners Of The "shop Without Sellers" Trained AI To Detect Thieves - Alternative View
The Owners Of The "shop Without Sellers" Trained AI To Detect Thieves - Alternative View

Video: The Owners Of The "shop Without Sellers" Trained AI To Detect Thieves - Alternative View

Video: The Owners Of The
Video: Nefarious: Merchant of Souls | Human Trafficking Documentary - Full Movie 2024, May
Anonim

Today, more and more stores are opening where goods do not need to be paid at the checkout, everything is built on self-service and there is not a single seller in the trading floor. However, this can attract thieves to such stores. Of course, no one has canceled the video surveillance system, but it has been significantly improved by training the AI to calculate the criminal before he commits theft.

Standard Cognition is responsible for the development of very interesting software. The system currently uses 27 cameras, which are controlled by a special algorithm. It records almost all the indicators of buyers: the speed and length of steps, the direction of sight, and even the product that the buyer is looking at at the moment. The program calculates how long a person looks at labels, monitors the movement of goods in the sales area, and so on. But most importantly, from all the information received, the program draws a conclusion about the "potential unreliability" of the buyer.

Five of the seven founders of Standard Cognition used to work at the US Securities and Exchange Commission, where they developed algorithms to detect fraudulent schemes, so the company has the necessary experience. As stated by Michael Suswell, one of the leaders of Standard Cognition, The company has already received an investment of US $ 11.2 million and has opened its first test store, where system deficiencies will be identified and improved. By 2020, the company plans to equip at least 100 stores with its system every day.

Vladimir Kuznetsov

Recommended: