STRASMORE/EXPLORE 2,170 QUERIES

Training rank against holdout result: 240 trials cut into fifths

Answered against 22 years of US equities and 12 years of US options data and published with the query that produced it. This result is stored as of 2026-08-02, from Can an LLM Find Alpha Factors?.

as of ranking 5×3read in context →
Training rank against holdout result: 240 trials cut into fifths — 5 rows by 3 columns, computed from US exchange, SIP and OPRA data.
training_groupavg_in_sample_sharpeavg_out_of_sample_sharpe
best fifth in training0.660.01
second fifth0.260.02
middle fifth-0.01-0.08
fourth fifth-0.24-0.03
worst fifth in training-0.630.13
Rows × columns
5 × 3
Computed
Completeness
No missing values
Source
US exchange, SIP and OPRA market data
Licence
Strasmore terms · free, no signup
Formats
JSON · CSV · the SQL below

What each column holds

Column definitions for Training rank against holdout result: 240 trials cut into fifths, derived from the stored result.
ColumnTypeRangeNotes
training_group text 5 distinct values
avg_in_sample_sharpe number -0.63 to 0.66
avg_out_of_sample_sharpe number -0.08 to 0.13

Computed from Strasmore's warehouse of US exchange, SIP and OPRA market data. Equity prices are delayed; options greeks and implied volatility are end-of-day. This result is stored, not recomputed on load — it is exactly the numbers that were returned on , and the query below is what returned them.

the exact SQL behind every number
WITH month_end AS (
    SELECT ticker,
           toStartOfMonth(toDate(toTimeZone(window_start, 'America/New_York'))) AS month_start,
           argMax(toFloat64(close), window_start) AS close_px
    FROM global_markets.delayed_stocks_minute_aggs
    WHERE ticker IN ('AAPL','ADBE','AMZN','BA','CAT','COST','CRM','CSCO','CVX','DE',
                     'DUK','GE','GOOGL','HD','HON','IBM','INTC','JNJ','JPM','KO',
                     'LMT','MCD','MMM','MRK','MSFT','NKE','NVDA','ORCL','PEP','PFE',
                     'PG','QCOM','SO','T','TGT','TXN','UNP','VZ','WMT','XOM')
      AND toDate(toTimeZone(window_start, 'America/New_York')) >= toDate('2015-12-01')
      AND toDate(toTimeZone(window_start, 'America/New_York')) <= toDate('2026-06-30')
      AND toDayOfMonth(toTimeZone(window_start, 'America/New_York')) >= 22
      AND (toHour(toTimeZone(window_start, 'America/New_York')) * 60
           + toMinute(toTimeZone(window_start, 'America/New_York'))) BETWEEN 570 AND 959
    GROUP BY ticker, month_start
),
lagged AS (
    SELECT ticker,
           month_start,
           close_px,
           lagInFrame(close_px) OVER (PARTITION BY ticker ORDER BY month_start
                                      ROWS BETWEEN 1 PRECEDING AND CURRENT ROW) AS prev_px
    FROM month_end
),
monthly_return AS (
    SELECT ticker, month_start, close_px / prev_px - 1 AS ret
    FROM lagged
    WHERE prev_px > 0
      AND month_start >= toDate('2016-01-01')
),
trial AS (
    SELECT arrayJoin(range(1, 241)) AS n
),
factor_month AS (
    SELECT t.n AS trial_id,
           m.month_start AS month_start,
           avgIf(m.ret, bitAnd(cityHash64(m.ticker, toString(m.month_start), t.n), 1) = 1)
         - avgIf(m.ret, bitAnd(cityHash64(m.ticker, toString(m.month_start), t.n), 1) = 0) AS long_short_ret
    FROM monthly_return AS m
    CROSS JOIN trial AS t
    GROUP BY trial_id, month_start
    HAVING countIf(bitAnd(cityHash64(m.ticker, toString(m.month_start), t.n), 1) = 1) > 0
       AND countIf(bitAnd(cityHash64(m.ticker, toString(m.month_start), t.n), 1) = 0) > 0
),
scored AS (
    SELECT trial_id,
           avgIf(long_short_ret, month_start <  toDate('2021-07-01'))
             / stddevSampIf(long_short_ret, month_start <  toDate('2021-07-01')) * sqrt(12) AS in_sample_sharpe,
           avgIf(long_short_ret, month_start >= toDate('2021-07-01'))
             / stddevSampIf(long_short_ret, month_start >= toDate('2021-07-01')) * sqrt(12) AS out_of_sample_sharpe
    FROM factor_month
    GROUP BY trial_id
    HAVING countIf(month_start <  toDate('2021-07-01')) >= 24
       AND countIf(month_start >= toDate('2021-07-01')) >= 24
),
ranked AS (
    SELECT trial_id,
           in_sample_sharpe,
           out_of_sample_sharpe,
           row_number() OVER (ORDER BY in_sample_sharpe DESC) AS in_sample_rank
    FROM scored
)
SELECT multiIf(in_sample_rank <=  48, 'best fifth in training',
               in_sample_rank <=  96, 'second fifth',
               in_sample_rank <= 144, 'middle fifth',
               in_sample_rank <= 192, 'fourth fifth',
               'worst fifth in training') AS training_group,
       round(avg(in_sample_sharpe), 2) AS avg_in_sample_sharpe,
       round(avg(out_of_sample_sharpe), 2) AS avg_out_of_sample_sharpe
FROM ranked
GROUP BY training_group
ORDER BY min(in_sample_rank)

Run your own version of this

The same 22 years of US equities and 12 years of options data are queryable in SQL or plain English. A free account runs 100 queries a day and takes no card.

More from this analysisCan an LLM Find Alpha Factors?
The twelve best trials in training, re-scored on five untouched years (Jul 2021 to Jun 2026) ranking 12×3 The best score climbs with the size of the search: best and average Sharpe by trials run ranking 9×3 240 coin flip factors scored on real prices: annualized Sharpe, Jan 2016 to Jun 2021 ranking 8×3 When market headlines publish, by New York clock hour ranking 24×2 When headlines actually land: article counts by ET clock hour, July 2026 ranking 24×4 Growth of one dollar: holding all year vs holding only November through April ranking 21×3 See all 2,170 queries →