THE Reserve Bank of Australia (RBA) will hold the official cash rate (OCR) steady, say students at the University of Melbourne.

Honours and Masters students in the Advanced Data Analysis class believe they have accurately predicted the upcoming cash rate decision ahead of the Reserve Bank of Australia’s board meeting on September 24.

Ledby Associate Professor Yong Song from the Department of Economics and using Artificial Intelligence, the programming language Python and Machine Learning techniques,15 of 17 student groups correctly predicted the RBA's decision to hold the cash rate on August 6.

Dr Song, whose research focuses on financial econometrics, interest rates, unemployment, and inflation, believes the models used by his class will be even more accurate in forecasting September’s decision.

“They have learned many Machine Learning techniques, they have collected lots of data to help them so they can apply statistical models to make predictions,” he said.

The students use data from the Australian Bureau of Statistics, the RBA and the Australian Stock Exchange.

Master of Applied Econometrics student Jiaxin Lai and his group used a 'Lasso Regression' model to narrow down the most relevant economic indicators.

“We've improved our model, and eventually we arrived at the decision that this cash rate will remain unchanged for the September quarter,” Jiaxin said.

Economics honours student Jingjing Li said although her group was also correct in its forecast for August, the model they’ve used to forecast the September 24 decision is far more robust.

“Last time, when we were learning, our methods were rather naive, because everything was based on a linear model… the particular model we're using now has more predictive power,” she explained.

Jingjing and her team believe the RBA cash rate will remain unchanged.

Master of Economics student Yifei Chen and her team are using data from the RBA and ABS, separating the time series data into two sets, a training set and a testing set.

The first set is used to train their machine learning model, the second set tests the actual result with the prediction result.

Yifei and her team also believe the cash rate will remain unchanged.

For Dr Song, constructing the forecasting project as group work and encouraging students to come together in person has had other benefits as well.

“Students start to chat and talk, ask questions and have lots of interactions during the class. It's very warm,” he explained. “I’ve enjoyed it. Students enjoy it. It's also a good way to repel loneliness and depression.”

Working in groups for several weeks allowed the students—who are from different parts of the Faculty of Business and Economics—to form solid relationships and learn from each other.

“One of my favourite parts about this project is how open-ended everything could be; it really sparked some great conversations between my team,” Jiaxin said.

As the students await the RBA's decision, Dr Song believes the experience will give them a competitive edge in the job market, showcasing their ability to tackle complex problems using advanced data analysis techniques.