The Bangko Sentral ng Pilipinas (BSP) is leveraging on artificial intelligence (AI) as it explores applications of machine learning techniques, particularly in the areas of natural language processing, nowcasting, and banking supervision.
Machine learning is a subfield of AI involving algorithms that deliver output based on patterns learned from data.
“Central banks’ interest in machine learning has been increasing over the years, mainly due to its potential to enhance the existing tools used for regular monitoring as well as its ability to uncover underlying relationships between data to better understand the economy and the financial system,” BSP Governor Benjamin Diokno said.
Natural language processing at the BSP is used to convert text into data to produce a quantitative summary, such as the news sentiment index and economic policy uncertainty index that are currently being developed.
The BSP also employs machine learning approaches to generate nowcasts of regional inflation and domestic liquidity. These models supplement the BSP’s existing suite of models for macroeconomic forecasting.
In banking supervision, the regulator aims to utilize machine learning techniques to enhance its data validation processes and better identify atypical data.
Diokno said machine learning offers diverse opportunities in central banking, especially when combined with techniques from other disciplines, such as econometrics and network science.
Nonetheless, the BSP chief highlighted several challenges associated with machine learning processes such as the black-box approach that could result in difficulties in interpreting the causal relationships models.
Like traditional econometric techniques, machine learning algorithms may also encounter some challenges in accurately predicting tail risk or low likelihood events.
The adoption of machine learning models would also necessitate investments in information technology infrastructure and capacity building as well as a change in the organizational mindset.
“As we build a stronger and more technologically advanced Philippine economy, the BSP will continue to explore ML applications that can be useful in the conduct of its key functions, while carefully taking note of the associated challenges,” Diokno said.