This post is part of a four-part summary of Google's Machine Learning Crash Course. For context, check out this post. This fourth module covers critical considerations when building and deploying ML models in the real world, including productionisation best practices, automation, and responsible engineering.
This post is part of a four-part summary of Google's Machine Learning Crash Course. For context, check out this post. This third module covers advanced ML model architectures.
This post is part of a four-part summary of Google's Machine Learning Crash Course. For context, check out this post. This second module covers fundamental techniques and best practices for working with machine learning data.
This post is part of a four-part summary of Google's Machine Learning Crash Course. For context, check out this post. This first module covers the fundamentals of building regression and classification models.
I like to revisit Google's Machine Learning Crash Course every now and then to refresh my understanding of key machine learning concepts. It's a fantastic free resource, published under the Creative Commons Attribution 4.0 License, now updated with content on recent developments like large language models and automated ML.
The notion that Japan has a labour shortage is widely accepted. The country's ageing and shrinking population leaves fewer working-age people for firms to hire. Businesses often cite difficulties finding workers as a reason for raising pay, and labour shortages are seen as a driver of inflation. However, Mizuho executive economist Momma Kazuo, in a commentary published on 21 January 2025, challenges this view. He argues that labour market conditions are more nuanced than commonly perceived and that declining real wages contradict the narrative of a general labour shortage. This post summarises key points from the report.
This post summarises key points from the latest economic commentary by Momma Kazuo, executive economist with Mizuho Research & Technologies and former assistant governor at the Bank of Japan. Published on 25 December 2024, this piece is part of a series of articles exploring issues in the Japanese and global economies. It highlights the risk of Japan's lost decades continuing and questions whether the country can overcome its demographic challenges.
The big story over the past two weeks has been the unwinding of the yen carry trade. This trade involves borrowing yen at low rates in Japan and investing the funds in higher-yielding foreign currencies, such as the US dollar or the Mexican peso. Many have argued that a surprise rate hike from the Bank of Japan on 31 July and disappointing US labour market data on 2 August triggered the collapse of this trade. As a result, the yen surged, equities stumbled, and government bonds rallied. While not much is known about the exact scale of the yen carry trade, this post explores two methods of proxying it.
Central banks in recent years have paid close attention to “inflation expectations” when setting monetary policy. But measuring these expectations is not always straightforward. Expectations can vary significantly depending on whether they are drawn from businesses, households, or professional forecasters. One of the more practical methods for gauging inflation expectations is by analysing bond market data. This post provides an overview of how this works.
Japanese FX intervention has been in the headlines lately, as the yen's depreciation has prompted Japanese authorities to step into the market multiple times over the past two years. According to media reports, the Ministry of Finance and the Bank of Japan likely intervened this past Thursday, 11 July, which saw the yen surge from nearly 162 JPY/USD to almost 157 JPY/USD. Official confirmation of the intervention won't arrive until 31 July, but we can estimate the scale of the intervention using BOJ accounts and money market broker forecasts.