Marcus Buckmann, Galina Potjagailo and Shobhit Rawat
What can synthetic intelligence reveal about corporations’ pricing selections from text-based enterprise intelligence? We use a big language mannequin (LLM) to quantify pricing narratives from stories documenting discussions through the Financial institution of England’s firm visits. The LLM is prompted to derive scores for output-price modifications and decompose them into determinants, together with direct and oblique enter prices, labour prices and demand. The ensuing measures get well economically significant alerts from corporations’ narratives over time, from weak demand following the worldwide monetary disaster (GFC) to broad value pressures and subsequent results by wage and value setting through the latest inflation surge. The most recent narratives level to marked value will increase following Center East battle, however to this point much less broad and chronic than in 2022.
Inside corporations’ pricing narratives: exploiting textual content sections from enterprise intelligence stories
Inflation information inform us how combination costs are altering however reveal little in regards to the elements shaping corporations’ pricing selections and the mechanisms driving inflation. To make clear these narratives ‘on the bottom’, Financial institution of England workers often meet firms throughout the UK, documenting discussions in firm go to stories. Alongside manually assigned firm go to scores, a typical report comprises data on the agency, resembling its location, employment and turnover, in addition to detailed qualitative notes summarising workers discussions with the contact on demand, prices, wages, margins, funding and costs. This enterprise intelligence supplies a direct qualitative view of how corporations understand financial circumstances, type expectations and clarify their selections. But these text-based stories have remained largely underexplored as a supply for systematically quantifying such narratives over time.
In ongoing analysis, we use an LLM (GPT‑5.4) to analyse these textual content sections. Our information set comprises 66,820 stories from January 2005 to September 2026, averaging round 260 monthly, though volumes have declined considerably over time (to 237 monthly in 2026). To handle prices, we analyse a random one third pattern as much as 2025 and the total pattern for 2026. The textual content sections have turn out to be considerably longer over time, with median size rising from 585 phrases in 2005 to 1,254 phrases lately, permitting a extra nuanced quantification of pricing narratives within the later a part of the pattern. The stories cowl 2,000–3,000 corporations per 12 months. Producers and medium-sized corporations are considerably over-represented relative to the UK enterprise inhabitants.
Utilizing an LLM to derive scores and decompositions of pricing determinants
For every report, the LLM quantifies reported and anticipated output-price modifications over the previous and subsequent three to 12 months relative to regular circumstances. This mirrors the Financial institution’s current observe of manually scoring corporations’ assessments however applies it systematically throughout the textual content. Importantly, relatively than merely monitoring whether or not costs are rising or falling, the LLM decomposition maps the elements cited by contacts to a set of financial determinants. This enables us to hint the evolution of corporations’ pricing narratives over time, akin to latest work on combination inflation narratives from newspaper articles. Evaluation on the Reserve Financial institution of Australia as a substitute quantifies enterprise intelligence into stand-alone scores utilizing dictionary strategies.
We instruct the LLM to separate the next six determinants in our most popular specification: direct energy-related prices, enter prices that pass-through not directly through provide chains resembling through vitality getting used to provide inputs, labour prices, demand, profit-margin adjustment, reflecting the extent to which corporations take in or move by increased prices, and strategic complementarities, which seize how corporations alter costs in response to rivals going through related pressures. Additional, any unexplained part is assigned to an unattributed class.
The LLM analyses the total textual content of every report and is instructed to assign contributions solely when an element is explicitly linked to corporations’ pricing selections. For instance, wage developments contribute to the labour prices part solely when described as influencing price-setting and obtain a zero contribution in any other case. Stories with inadequate pricing data are excluded. Averaging these report-level scores and determinant contributions produces combination and sector-level month-to-month scores and decompositions.
The LLM recovers intuitive inflation narratives.
Chart 1 exhibits the LLM rating for realised output costs (black line), demeaned over the pattern interval and rescaled to CPI inflation. It tracks CPI inflation (dotted blue) intently, albeit with better month-to-month volatility, regardless of a bigger unexplained part following the GFC and through the latest inflation episode. The LLM rating can also be extremely correlated with Financial institution staff-assigned firm go to scores (yellow), however often turns sooner, resembling in 2016 and 2021, and unwinds extra rapidly thereafter, most notably in 2023.
Chart 1: LLM rating of enterprise contacts’ output value modifications over the previous three to 12 months, in opposition to guide Financial institution workers (Brokers’) scores and CPI inflation
Notes: LLM output-price scores (black line), demeaned and rescaled to CPI inflation (dotted line, imply of two.9%, max: 11.1% in October 2022). Aggregated throughout all stories used. Unique scale for LLM rating: [-100;100], Financial institution workers (Brokers’) scores: [-5;5].
The LLM decomposes the rating into determinants, proven in Chart 2, total capturing an economically significant inflation anatomy over time. Throughout the GFC, the LLM decomposition factors to cost pressures dominated by weak demand, adopted by downward stress from strategic pricing and unattributed elements, though this weak point was much less evident in CPI inflation. Labour prices additionally weighed on costs within the subsequent restoration. In 2014–15 and through the Covid-19 pandemic, decrease international oil and commodity costs have been mirrored in weaker oblique value pressures, although much less so than in CPI inflation. Following the Brexit referendum, corporations’ narratives as a substitute pointed to rising non-labour prices and a bigger unattributed part, probably reflecting heightened uncertainty.
Chart 2: LLM decomposition of enterprise contacts’ output value modifications over previous three to 12 months
Pricing narratives through the 2021–23 inflation and lately
In 2021, corporations reported broad-based direct and oblique value pressures, supported by sturdy demand and smaller contributions from margins and strategic pricing. Throughout 2022–23, labour prices and price-setting channels turned more and more vital, notably amongst service suppliers, as demand weakened. By 2024–25, labour prices had emerged because the dominant upward driver, coinciding with introduced will increase within the Nationwide Residing Wage and employers’ Nationwide Insurance coverage contributions. To get a extra nuanced image, in Chart 3 we additionally individually combination outcomes by items producers and repair suppliers, rescaled to items and companies CPI inflation, respectively.
Chart 3: LLM decomposition of output value modifications, by items and companies producers, from 2021
Notes: Demeaned and rescaled LLM output-price scores (black line) and decompositions (bars), aggregated individually by items and companies producers. Demeaned and rescaled primarily based on items inflation (imply: 2.3%) and companies inflation (imply: 3.6%), respectively.
The consequences from the Center East battle on realised pricing narratives have to this point remained comparatively subdued. A brief rise in direct value pressures was adopted by some oblique value pressures in latest months. Nonetheless, these results stay way more muted than in 2021–23 and have been accompanied by weak labour value pressures and subdued demand. For companies corporations, the decomposition additionally suggests sustained value pressures from strategic pricing and revenue margins, pointing to some continued means to move by increased prices into costs. Nonetheless, in contrast with 2022–23, weaker wage pressures could present better scope for corporations to soak up a part of these pressures relatively than move them by.
Previous versus anticipated narratives
Round turning factors, what companies count on could also be extra informative than what they report in regards to the latest previous. We subsequently individually quantify anticipated output-price modifications and their determinants over the subsequent three to 12 months. Chart 4 compares previous and anticipated contributions: each have a tendency to maneuver intently collectively, probably reflecting each the issue of totally separating previous and future developments inside the stories and contacts’ tendency to extrapolate present circumstances. The most important divergences emerged round main shocks. In early 2021, anticipated value pressures strengthened forward of realised pressures, notably by direct and oblique prices and revenue margins. Because the begin of the Center East battle, direct value pressures have risen extra sharply in expectations than in realised narratives and stay elevated, whereas a short lived rise in anticipated oblique prices seems to be feeding into realised pressures, albeit a lot lower than in 2022–23. Sooner or later, we purpose to discover whether or not anticipated pricing narratives comprise main data for inflation.
Chart 4: Evaluating contributions to previous and anticipated output-price modifications
Notes: Chosen LLM decomposition contributions for previous three to 12 months (strong) and subsequent three to 12 months (dashed) narratives, 2020–26, aggregated throughout all stories, no rescaling, 12-month one-sided transferring common.
Validating the LLM determinants in opposition to exterior sequence
Lastly, the LLM-derived pricing determinants intently resemble established macroeconomic indicators. Chart 5 exhibits, for instance, that the direct value part tracks UK CPI vitality inflation, whereas the demand part aligns nicely with a Financial institution of England workers estimate of the UK output hole, utilizing an method primarily based on a state-space mannequin just like these developed for the Euro space. Given the uncertainty surrounding output-gap estimates in actual time, the LLM-derived measure of corporations’ demand pressures could present a helpful complementary indicator. This implies that the decomposition recovers economically significant alerts from corporations’ narratives regardless of not being designed to immediately determine combination structural inflation drivers.
Chart 5: Chosen LLM decomposition contributions in contrast in opposition to exterior sequence
Notes: LLM direct-energy (left) and demand (proper) contributions from decomposition of realised output-price modifications over previous three to 12 months. The LLM contributions are rescaled to the corresponding dashed-line exterior sequence. The output hole is a Financial institution of England workers estimate from a state-space mannequin estimated over 1988 Q1 to 2026 Q3 and is linearly interpolated from quarterly to month-to-month frequency for plotting.
Sources: Financial institution of England workers calculations, ONS and authors’ calculations.
From qualitative intelligence to quantitative proof for coverage
We present how LLMs can rework narrative enterprise intelligence into quantitative indicators whereas preserving significant distinctions between pricing determinants. The method enhances Financial institution workers’s qualitative assessments by offering a constant framework for evaluating narratives throughout corporations, sectors and time. Past monitoring whether or not corporations report costs rising or falling, it helps uncover the drivers behind these modifications and distinguish inflation episodes by their narrative anatomy. Within the present conjuncture, for instance, it means that value pressures following the Center East battle stay concentrated in direct prices, with restricted proof of the broader propagation mechanisms seen through the 2021–23 inflation surge. Extra usually, it opens new prospects for turning qualitative enterprise intelligence into well timed quantitative proof for financial evaluation and coverage.
Marcus Buckmann works within the Financial institution’s Superior Analytics Division, Galina Potjagailo works within the Financial institution’s Financial Coverage Innovation Lab and Shobhit Rawat works within the Financial institution’s Company Community.
If you wish to get in contact, please electronic mail us at bankunderground@bankofengland.co.uk or depart a remark under.
Feedback will solely seem as soon as permitted by a moderator, and are solely printed the place a full title is equipped. Financial institution Underground is a weblog for Financial institution of England workers to share views that problem – or help – prevailing coverage orthodoxies. The views expressed listed here are these of the authors, and should not essentially these of the Financial institution of England, or its coverage committees.
Share the publish “Synthetic intelligence meets enterprise intelligence: the anatomy of inflation”
