Climate services for finance, lessons learned and feedback for the public sector
Bibliographic record
Abstract
There has been a recent increase in demand for climate data and insights on the potential impacts of climate change. This is particularly true in the finance sector - in the past 18 months financial regulators in the UK, Europe, USA, Canada and elsewhere globally have all stipulated that large and listed firms are legally required to understand their climate risk and do something to mitigate that risk. The finance sector is not well placed to generate these climate risk insights, motivating the rise of multiple climate risk data providers.Climate X is a private-sector provider of climate risk analytics and services. Our in-house science team makes use of a wealth of publicly available data in the science that underpins the services we provide; data such as climate models and remote sensing data. We provide science as a service and deliver our data in a way that is useful and used within the finance sector.I will briefly outline how we use publicly available data to derive climate risk information that is relevant to the finance sector, and how we deliver that data in away that is meaningful to our end users. I will discuss why the data in its raw form doesn’t address sector requirements, and feedback from the sector on how publicly available climate and remote sensing data is used. I will summarise lessons learned from our engagement with finance on how the public sector could provide data which is tailored to end user needs, and is more immediately relevant and useful for adaptation action in this industry.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.014 | 0.069 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.002 | 0.004 |
| Science and technology studies | 0.003 | 0.002 |
| Scholarly communication | 0.015 | 0.012 |
| Open science | 0.001 | 0.005 |
| Research integrity | 0.007 | 0.009 |
| Insufficient payload (model declined to judge) | 0.106 | 0.037 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".