POID Research Seminar
Faster, richer, cheaper: can AI help us improve UK price data and track trade costs in real time?
Richard Davies (LSE and CEP), Josh Hellings (LSE), Finn Mcevoy (LSE)
Tuesday 06 February 2024 11:00 - 12:00
Many of our seminars and public events this year will continue as in person or as hybrid (online and in person) events.
Please check our website listings and Twitter feed @STICERD_LSE for updates.
Unless otherwise specified, in-person seminars are open to the public. Please ensure you have informed the event contact as early as possible.
Those unable to join the seminars in-person are welcome to participate via zoom if the event is hybrid.
About this event
This live project introduces new price microdata for UK. The data aims to allow automated grocery inflation estimates and a real-time interrogation of the geographic sources of price changes. Our dataset contains 19m prices collected since July 2023 from retailers representing over 70% of UK grocery expenditure. The prices, collected daily via automated web access, offer insights into the frequency, timing, and distribution of price changes. Compared to existing UK microdata on pricing, our dataset is larger, is far richer (capturing information on, for example, calorific content of foods), and is available at a lag of around 12 hours, rather than 30+ days. Through a LLM classification process, we investigate inflation, producing daily estimates. We extend the analysis by identifying the country of origin for over 60,000 products. The origin data allows us a first look at the sources of food price inflation as well as the impacts of trade frictions at the GB-EU border. We hope the results, the methodology, and the dataset, will have a wide range of research and policy uses.