Scientists from the Stanford Institute for Artificial Intelligence have created an algorithm that allows you to estimate the level of wages based on job descriptions. Writes about it VentureBeat.
To compare the relationship between ad text and salary, the researchers collected more than a million employee search records. They then used the natural language processing model BERT and with its help processed 800,000 vacancies.
In the process of testing the system on the remaining records, it turned out that the algorithm predicts the correspondence between the job description and salary with an accuracy of 87%. In comparison, using only ad titles and geographic locations produced accurate predictions only 69% of the time.
Using the algorithm, the scientists also identified a relationship between the presence of certain certificates and the prospects for a salary increase. Possession of such information will help employees choose the really necessary training courses, they believe.
Lead researcher Sarah Bana noted that not only applicants will benefit from the algorithm. Employers can use this information to better invest in human capital and retrain certain employees early, she says.
For authorities, the data will help promote vocational education programs and understand the economic value of skills, Bana added.
“Tools like this will help jobseekers improve their job prospects, employers improve their workforce, and governments respond to immediate changes in the economy,” the researcher said.
In the future, Bana hopes to develop a web-based application where employees or companies can explore added value by upgrading skills or moving to a new location.
The scientist will also try to characterize the contribution of various words to the salary forecast.
“Ideally, we will colorize the words in messages from red to green, where dark red words are associated with low pay and dark green with high pay,” she says.
Recall that in May, the Singapore authorities talked about the massive introduction of robot assistants by local businesses due to a shortage of labor.
In June 2021, scientists found that automation and artificial intelligence led to a 50-70% drop in US wages over the past 40 years.
Subscribe to Cryplogger AI at TikTok!
Found a mistake in the text? Select it and press CTRL+ENTER
Scientists from the Stanford Institute for Artificial Intelligence have created an algorithm that allows you to estimate the level of wages based on job descriptions. Writes about it VentureBeat.
To compare the relationship between ad text and salary, the researchers collected more than a million employee search records. They then used the natural language processing model BERT and with its help processed 800,000 vacancies.
In the process of testing the system on the remaining records, it turned out that the algorithm predicts the correspondence between the job description and salary with an accuracy of 87%. In comparison, using only ad titles and geographic locations produced accurate predictions only 69% of the time.
Using the algorithm, the scientists also identified a relationship between the presence of certain certificates and the prospects for a salary increase. Possession of such information will help employees choose the really necessary training courses, they believe.
Lead researcher Sarah Bana noted that not only applicants will benefit from the algorithm. Employers can use this information to better invest in human capital and retrain certain employees early, she says.
For authorities, the data will help promote vocational education programs and understand the economic value of skills, Bana added.
“Tools like this will help jobseekers improve their job prospects, employers improve their workforce, and governments respond to immediate changes in the economy,” the researcher said.
In the future, Bana hopes to develop a web-based application where employees or companies can explore added value by upgrading skills or moving to a new location.
The scientist will also try to characterize the contribution of various words to the salary forecast.
“Ideally, we will colorize the words in messages from red to green, where dark red words are associated with low pay and dark green with high pay,” she says.
Recall that in May, the Singapore authorities talked about the massive introduction of robot assistants by local businesses due to a shortage of labor.
In June 2021, scientists found that automation and artificial intelligence led to a 50-70% drop in US wages over the past 40 years.
Subscribe to Cryplogger AI at TikTok!
Found a mistake in the text? Select it and press CTRL+ENTER
