Lab
The advanced user area. Analysis runs are started here, all parameters are set only here, and the models' internal results are examined here.
Run list
What it is: The list of all analysis runs started: number, status, type, start time; a progress bar for running ones and the error message for failed ones.
What data feeds it: The analysis_run table (/api/analysis/runs). While a run is in progress, the list refreshes every few seconds.
What it shows: FULL runs are the walk-forward evaluation of the five models (A · Graph diffusion, B · Cross-sectional ranking, C · Change detection, D · Consensus and W · Weighted wave); REPLAY runs regenerate a past range "as if live"; the LIVE row is the daily pipeline's live signal stream.
What can be concluded from it: If the application shuts down while a run is in progress, that run becomes "FAILED" and the reason is recorded. The other screens always use the latest successful FULL run.
New run and replay
What it is: The "New" button opens the step-by-step parameter form, the "Replay" button the as-if-live replay form.
What data feeds it: The default values come from the /api/analysis/defaults endpoint, that is, from the application.yml file.
What it shows: The period, walk-forward windows, factor window, model parameters, consensus rule and transaction cost are set. In a replay, each day of the selected range is generated only from data up to that day.
What can be concluded from it: A full run takes 15–20 minutes on real data. Trying to improve the result by changing parameters increases the risk of overfitting the same data; whether a change really helps can only be seen in later live results.
The investment information, comments and recommendations given here are not within the scope of investment advisory services. Investment advisory services are provided under an investment advisory agreement to be signed between a client and brokerage houses, portfolio management companies, or banks that do not accept deposits. The signals here are produced from historical data with statistical models, are shown the same to everyone and are not personalised; they may not suit your financial situation or your risk and return preferences. Therefore, making investment decisions based solely on the information given here may not produce results that meet your expectations.