New Delhi: A new algorithm can predict the future market value of crops in India and help farmers maximise profits on their investments.
The algorithm has been developed by a team of researchers from Pennsylvania State University, US, who hope the system will help address the alarming rate of suicides among indebted farmers in India.
At least 10,349 people engaged in the farm sector committed suicide in 2018, according to the National Crime Records Bureau. According to Amulya Yadav, principal investigator on the project, farmers are driven to take the extreme step because of financial distress and their inability to sell crops at profitable rates because of widespread fluctuation in India’s market prices.
“In India, the government has set minimum support prices for crops, but does not try to explicitly force these prices upon the buyers,” said Yadav in a press release by the university.
“The actual price at which the crop sells at market is based on supply and demand,” he added.
To create the algorithm, the team analysed data records of more than 1,300 Indian markets from the past 11 years, which included maximum and minimum prices of every crop sold.
They then developed a deep-learning model — deep learning is a form of machine learning, the technology at the heart of artificial intelligence, that powers Siri and Alexa, for example — to find useful patterns from the data.
The resulting algorithm, the researchers said, guides farmers on where to sell crops and when, so they know where they will get the best prices at a given time.
Relieving farmers’ distress
Farmers, Yadav said, didn’t have to factor in harvest costs alone when calculating returns — besides buying seeds, fertilizer and equipment, they also have to transport their harvest to markets.
The government has set a minimum support price (MSP) for some crops, which it buys from farmers to assure guaranteed returns.
However, if farmers are unable to sell their crops at the MSP, Yadav added, they default on their loans or fail to make a profit, which pushes them into financial distress.
Government markets that buy crops at the minimum support price are often far away from farmers’ villages, which increases transportation and fuel costs, the researchers said.
Yadav added that the government only bought a limited quota, which means the remaining sellers have to go back dejected.
“They end up selling their crops to third-party vendors that don’t guarantee minimum support prices, and don’t make a profit,” Yadav said.
The algorithm they have made, the researchers claimed, can accurately predict future market prices based on past pricing and volume patterns.
“We’re trying to make a prediction to him or her (farmers) as to where and when they should sell their crop,” Yadav said.
“Instead of selling their crops on the very next day after harvest in the local market, this algorithm could potentially give a recommendation that they should wait five days and travel 40 kilometres to a different market, where the prices are predicted to be very high,” he added.