Research
MSc Dissertation · Individual ResearchFinancial ML · Model Reliability · Markets

When Financial Transformers Look Predictive

Separating temporal forecasting skill from static cross-sectional structure

The model looked predictive when all assets were pooled together. A simple asset-identity baseline did even better, and performance fell to roughly random when the model had to predict changes within the same asset.

Central findingStrong pooled discrimination did not establish temporal forecasting skill.

Evidence

The result in context

Transformer pooled ROC-AUC
0.790
Discrimination across all asset windows combined.
Training-only static asset prior
0.824
A baseline using persistent asset-level information.
Pair-weighted within-asset ROC-AUC
0.492
Roughly random when comparisons stay within the same asset.
Learned models passing the temporal-skill gate
0 / 5
On this page

Question

Was the model learning how markets change through time, or mostly recognising persistent differences between assets?

A controlled investigation into whether a strong pooled Transformer result represented genuine temporal forecasting skill.

A 60-session market window enters the Transformer; pooled, static-prior, within-asset, identity, chronology and simulation diagnostics then test what supports the reported score.

Initial evidence

A result that looked convincing

Across a pooled test set, the Transformer reached a ROC-AUC of 0.790. ROC-AUC measures how well a model separates two outcomes across possible decision thresholds; 0.5 is random and 1.0 is perfect ranking.

The dataset covered 79 assets, 60-session input windows and a 10-session prediction horizon. The apparent signal was large enough to deserve a more difficult question: what exactly was the model using?

Challenge to the result

A static baseline did better

A training-only prior based on persistent asset identity reached 0.824, higher than the neural model. That did not prove the Transformer used asset identity, but it showed that strong pooled ranking could arise without forecasting changes through time.

When evaluation was restricted to comparisons within the same asset, pair-weighted ROC-AUC fell to 0.492, approximately random.

Temporal evidence explorer

What survives the next control?

Move from the attractive pooled score to the test that the research question actually requires.

Transformer ROC-AUC0.790

Across every asset window combined, the model appeared to separate the two outcomes well.

Promising initial evidence, but not yet evidence of temporal skill.
  1. Pooled0.790
  2. Static prior0.824
  3. Within asset0.492
  4. Asset identityDetected
  5. ChronologyHeld out
  6. Simulation1,040
  7. Conclusion0 / 5

Interactive evidence

Pooled discrimination did not survive within-asset evaluation

ROC-AUC by evaluation frame. Higher is better; 0.50 is chance-level discrimination.

Read: The static asset prior led on pooled ROC-AUC, while the conditioned Transformer fell below chance within assets.

Data table · 3 verified rows
Complete dataset
ModelPooled Roc AucWithin Asset Roc Auc
Transformer0.7898140.491638
Transformer, No Asset ID0.7154770.47257
Static Asset Prior0.8239060.5

Diagnostics

The evidence was tested from several directions

Chronology checks, identity controls and 1,040 controlled simulation runs separated temporal signal from static cross-sectional structure. None of five learned models passed the pre-specified temporal-skill gate.

The conclusion is deliberately narrow: this experiment did not establish temporal forecasting skill. It is not a claim that Transformers never work in finance.

Interactive evidence

Static heterogeneity lifted pooled scores without temporal skill

Controlled simulation at zero dynamic signal and persistence 0.7.

Read: As cross-asset prior heterogeneity rose, the static-prior pooled score climbed to 0.899 while within-asset classification stayed near 0.50.

Data table · 4 verified rows
Complete dataset
Prior HeterogeneityAsset Prior Pooled Roc AucClassifier Within Roc Auc
00.4991180.496634
0.750.6919170.496796
1.50.8170730.504159
2.50.8991380.503338

Interactive evidence

The same diagnostic responded when temporal signal was present

Controlled simulation at zero prior heterogeneity and persistence 0.7.

Read: Within-asset ROC-AUC rose monotonically with dynamic signal, validating the diagnostic rather than the original headline model.

Data table · 4 verified rows
Complete dataset
Dynamic SignalClassifier Within Roc AucReversal Auc Drop
00.496634-0.002615
0.50.6111190.213772
10.7152640.425535
1.50.7871030.571246

Interpretation

Model evaluation begins after the headline metric

A model can rank pooled observations well while failing at the prediction task a practitioner actually cares about. Baseline design and evaluation structure were therefore more informative than another round of architecture tuning.

The broader lesson is to ask what information a metric permits the model to exploit before treating that metric as evidence of a useful forecasting mechanism.

Reproducibility

Frozen evidence and explicit provenance

The final dissertation repository is frozen. Its committed reports and figures form the preserved research record.

Limitations

What this evidence does not establish

  • Repeated inspection of the historical test period made later analysis adaptive rather than a pristine untouched confirmation.
  • The result is specific to the assets, horizon, labels and experimental design studied; it does not imply universal Transformer failure or universal asset-identity leakage.

Source and reproducibility

Trace the evidence

Source code, evaluation outputs and supporting material are available in the repository.

View repository
  1. Frozen dissertation repositoryassets/readme/graphical_abstract.svgCommit / evidence ID: 81d129902521303c264b6c05f7a7a344c5f39d54
  2. Headline resultsreports/tables/ifddrp_identity_dynamic_information_decomposition.csvCommit / evidence ID: 81d129902521303c264b6c05f7a7a344c5f39d54
  3. Controlled simulationreports/tables/prp1_study_a_independent_simulation_results.csvCommit / evidence ID: 81d129902521303c264b6c05f7a7a344c5f39d54