{"@attributes":{"version":"2.0"},"channel":{"title":"staticnotes.org","link":"\/","description":"Recent blog posts from Rob on staticnotes.org","generator":"Hugo -- gohugo.io","language":"en-US","lastBuildDate":"Sun, 18 Jan 2026 20:00:00 +0000","image":{"url":"https:\/\/staticnotes.org\/favicon.ico","title":"staticnotes.org"},"item":[{"title":"UK house price changes in real terms","link":"\/posts\/uk-house-prices\/","pubDate":"Sun, 11 Jan 2026 00:00:00 +0000","guid":"\/posts\/uk-house-prices\/","description":"

This post is a response to a newspaper article I read this morning. Every month the FT is reporting on how the housing market in the UK is performing as people love to talk about it:<\/p>\n

\n

UK house prices rise less than expected in 2025 as growth slows<\/strong><\/p>\n

UK house prices rose by 0.6 per cent in 2025 after a slowdown at the end of the year, according to lender Nationwide. […] Prices fell 0.4 per cent between November and December to an average of \u00a3271,068. Both figures were below analysts\u2019 expectations of a 1.2 per cent annual rise and a 0.1 per cent month-on-month expansion. FT Weekend (02.01.2026)<\/em><\/p>\n<\/blockquote>\n

I am asking myself how useful this statistic is for the average reader, especially for a reader who wants to buy or sell a property.<\/p>\n

Two issues are immediately obvious:<\/p>\n

    \n
  1. The average yearly house price change across all of the UK might not agree with the house price performance in the areas I live in or I want to move to. There are also difference by house type, e.g. flat vs. detached house vs. terraced house. Different types of property might even perform in opposite directions.<\/li>\n
  2. British people often view property, at least partially, as an investment opportunity. However, in those cases it would help to at least report the real (inflation-adjusted) house price change, not just the nominal change. An increase of 0.6% in nominal house prices sounds different when one doesn’t mention that inflation in 2025 was around 3.6% (UK CPI). Meanwhile other forms of investments did quite well. The FTSE 100 nominally returned 21.4% (which to be fair was a positive outlier this year compared to an average of 6% over the last 10 years).<\/li>\n<\/ol>\n

    Fortunately, it is not that difficult to compute real house prices more closely to my situation. The raw data is openly available via API:<\/p>\n

      \n
    1. The HM Land Registry registers the ownership of property in the UK and provides aggregate monthly data of the average transactions by region and property type.<\/li>\n
    2. The Office for National Statistics (ONS) provides monthly inflation data (CPI) for the UK.<\/li>\n<\/ol>\n

      So, in this post I want to compute and visualize how real flat and detached house prices in specific areas performed both nominally and in real terms.<\/p>\n

      \n \n Querying the housing price data\n <\/a>\n<\/h2>

      I am using the UK House Price Index of the Land Registry API:<\/p>\n

      \nhttp:\/\/landregistry.data.gov.uk\/data\/ukhpi\/region\n \n  \n \n <\/path>\n <\/svg>\n <\/span>\n \n \n<\/a><\/p>\n

      This allows me to query the monthly average house price value for different regions and property types. Important to note here is that this data is based on the succesful property transactions in a region which we use here as an approximation of the average value of similar properties in the region (that were or weren’t sold).<\/p>\n

      I am based in London and interested how the housing market performs close to me or areas that I am interested living in. So I will query the data for all London boroughs as well as some South England regions around London: Kent, Surrey, Buckinghamshire, and Oxfordshire.<\/p>\n

      I then resample the monthly data to quarterly data by taking the mean across the 3 months of a quarter.<\/p>\n

      I then store all the data in parquet files. You can find them \nhere\n \n  \n \n <\/path>\n <\/svg>\n <\/span>\n \n \n<\/a>.<\/p>\n

      \n \n Inspecting the data\n <\/a>\n<\/h2>

      Let’s have a look at how the data is stored in the file:<\/p>\n

      import<\/span> pandas<\/span> as<\/span> pd<\/span>\n<\/span><\/span>import<\/span> warnings<\/span>\n<\/span><\/span>import<\/span> matplotlib.pyplot<\/span> as<\/span> plt<\/span>\n<\/span><\/span>pd<\/span>.<\/span>set_option<\/span>(<\/span>'display.float_format'<\/span>,<\/span> lambda<\/span> x<\/span>:<\/span> '<\/span>%.2f<\/span>'<\/span> %<\/span> x<\/span>)<\/span>\n<\/span><\/span>warnings<\/span>.<\/span>simplefilter<\/span>(<\/span>'always'<\/span>,<\/span> category<\/span>=<\/span>UserWarning<\/span>)<\/span>\n<\/span><\/span><\/code><\/pre><\/div>
      Here I am loading the file for the different counties that I am interested in:<\/p>\n
      df_regions<\/span> =<\/span> pd<\/span>.<\/span>read_parquet<\/span>(<\/span>'.\/data\/uk_house_prices.parquet'<\/span>)<\/span>\n<\/span><\/span>df_regions<\/span>[<\/span>'is_london_borough'<\/span>]<\/span> =<\/span> False<\/span>\n<\/span><\/span>df_regions<\/span>.<\/span>sample<\/span>(<\/span>5<\/span>,<\/span>ignore_index<\/span>=<\/span>True<\/span>)<\/span>\n<\/span><\/span><\/code><\/pre><\/div>
      \n