Xiphers Research·← Back to indexDEEN

RV3 — will today be a trend day? · NQ

NQ · decision at 09:30 New York · 1607 daily bars up to 2026-08-14

Verdict — NQ

Can we tell at 09:30 whether today will be a trend day (RTH body ratio ≥ 0.6)?

Criterion not met — BSS -1.2 % [-2.7 ; 0.2], AUC 52.4 %, accuracy 62.2 % against a base rate of 36.4 %, n = 905 days pooled forward.

Criterion: BSS > 2 and AUC ≥ 57, pooled forward across 2023–2026

Setup
Decision time09:30 New York — bars up to t−1 complete, the opening print and every tick of session t before 09:30
Targetbody ratio br = |rc − ro| / (rh − rl) ≥ 0.6
Data window2020-05-29 to 2026-08-14 · 1607 daily bars · last day 2026-08-14
Walk-forwardDev ≤ 2022 (definitions only), test 2023 / 2024 / 2025 / 2026, expanding with a yearly refit
ModelL2 logistic regression on 15 preregistered set C features, standardised on the training window; C from inner validation (the last training year). Features: gap_atr, abs_gap_atr, on_range_atr, ln_on_relr, on_vol_rel, on_delta_norm, open_pos_on, on_ext_recency, pre_range_share, on_high_vs_rh1_atr, on_low_vs_rl1_atr, open_pos_va, prev_ln_relr_rth, prev_ln_relr_mean5, prev_atr5_atr20
HoldoutThe PX holdout from 2026-05-01 concerns the PX theses on the tick store. This study is a walk-forward over 2023 to 2026 on daily data — explicitly approved by the user for regime rounds 1 and 2. Every test year is computed from data before it only; no fit ever sees its own test slice.

Test years and pooled forward

Every row is a forecast over the same days. Base rate, majority and persistence are the baselines; the model has to beat them, otherwise it does not count.

RowYearnBase Rate %Acc %AUC %BrierBSS %
Base Rate202324839.560.550.00.23940.0
Majority202324839.560.5
Persistence202324839.560.545.20.2421-1.1
Model (LogReg)202324839.558.552.70.2395-0.0
Base Rate202425137.562.550.00.23540.0
Majority202425137.562.5
Persistence202425137.562.552.80.23520.1
Model (LogReg)202425137.560.251.90.2431-3.2
Base Rate202525133.566.550.00.22710.0
Majority202525133.566.5
Persistence202525133.566.553.30.22660.2
Model (LogReg)202525133.565.749.40.2300-1.3
Base Rate202615534.265.850.00.22720.0
Majority202615534.265.8
Persistence202615534.265.852.40.22680.1
Model (LogReg)202615534.265.853.60.22670.2
Base Ratepooled90536.463.652.80.23280.0
Majoritypooled90536.463.6
Persistencepooled90536.463.650.50.2333-0.2
Model (LogReg)pooled90536.462.252.40.2357-1.2

Block bootstrap (20-day blocks, 1000 runs, pooled forward): BSS 95 % interval [-2.7 ; 0.2].

Confusion matrix pooled: true 0 correct 532 of 576, true 1 correct 31 of 329 (recall 0 = 92.4 %, recall 1 = 9.4 %).

Regularisation chosen per refit — 2023: C = 0.01, n_train = 581 · 2024: C = 1, n_train = 829 · 2025: C = 0.01, n_train = 1080 · 2026: C = 0.01, n_train = 1331.

Calibration and sharpness

Decilenmean p %observed %difference
19132.031.9-0.1
29136.137.41.3
39138.226.4-11.8
49139.539.60.1
59140.538.5-2.0
69041.738.9-2.8
79043.140.0-3.1
89044.836.7-8.1
99047.235.6-11.7
109052.638.9-13.7

Sharpness: p ≥ 0.7 on 0.0 % of the days (n = 0), hitting — % there · p ≤ 0.3 on 1.5 % (n = 14), hitting 71.4 % there.

How to read this report
Base Ratethe unconditional frequency in the training window, and at the same time the constant comparison forecast.
Baselinethe number a model has to beat. Three of them here: base rate, majority (always the more frequent class) and persistence.
Persistencethe forecast “today like yesterday” — the value of the same target on the previous day, turned into a rate.
BSSBrier skill score: what percentage of the base rate constant's Brier score the model saves. 0 means equally good, negative means worse.
AUCthe probability that a random positive day is scored above a random negative one. 50 is a coin flip.
Brierthe mean squared error of the probability. Smaller is better.
Sharpnesson what percentage of the days the model says something clear (p ≥ 0.7 or ≤ 0.3) and how often it hits there. A calibrated model without sharpness is useless.
Value Areathe price band [rval, rvah] in which 70 % of the RTH volume traded. Always the previous day's here.
Trend Dayan RTH with a body ratio ≥ 0.6 — the body of the daily candle fills at least 60 % of its range.
Body Ratiobr = |rc − ro| / (rh − rl), computed on the RTH session.
relrRTH range divided by the median of the 20 previous RTH ranges. relr ≥ 1 means: today is bigger than the typical one of the last four weeks.
Walk-Forwardevery test year is computed from a model that has only seen data before it; the training window grows with every year. No fit sees its own test.

The numbers in this report are recomputed on every publish — from data/daily-bars-*.json and data/open-features-*.json, which the extractor builds from the tick store.

Run: 1607 daily bars, 0.4 s.