Backtest Results (2020 – 2025)
Avg 90-Day Return by Score Tier  ·  Signal vs TSX Benchmark  ·  Hover bars for detail
0% 2% 4% 6% 8% 10% Score 90–100 ▸ Signal avg: +8.4% · TSX avg: +4.3% · Alpha: +4.1% · Hit rate: 69% · 84 signals Score 90–100 ▸ TSX benchmark: +4.3% over same 90-day windows +8.4% +4.3% 90–100 69% hit Score 75–89 ▸ Signal avg: +7.7% · TSX avg: +4.3% · Alpha: +3.4% · Hit rate: 63% · 336 signals Score 75–89 ▸ TSX benchmark: +4.3% over same 90-day windows +7.7% +4.3% 75–89 63% hit Score 60–74 ▸ Signal avg: +6.3% · TSX avg: +4.0% · Alpha: +2.3% · Hit rate: 57% · 545 signals Score 60–74 ▸ TSX benchmark: +4.0% over same 90-day windows +6.3% +4.0% 60–74 57% hit Score 40–59 ▸ Signal avg: +5.9% · TSX avg: +3.7% · Alpha: +2.3% · Hit rate: 52% · 608 signals Score 40–59 ▸ TSX benchmark: +3.7% over same 90-day windows +5.9% +3.7% 40–59 52% hit Score 20–39 ▸ Signal avg: +6.5%* (median −2.9% — avg skewed by micro-cap outliers) · TSX avg: +3.2% · Hit rate: 46% · 102 signals Score 20–39 ▸ TSX benchmark: +3.2% over same 90-day windows +6.5%* +3.2% 20–39 46% hit Signal avg return TSX 60 benchmark * avg skewed — see note below

1,676 signals backtested across TSX & TSXV companies from 2020 to 2025. Return measured over the 90 calendar days following the signal date. Benchmark is the iShares S&P/TSX 60 ETF (XIU.TO) return over the same 90-day window.

Score Tier Signals Signal Avg Median TSX 90d Alpha Hit Rate
90 – 100 Exceptional 84 +8.4% +6.5% +4.3% +4.1% 69%
75 – 89 Strong 336 +7.7% +5.3% +4.3% +3.4% 63%
60 – 74 Moderate 545 +6.3% +1.9% +4.0% +2.3% 57%
40 – 59 Weak 608 +5.9% +1.2% +3.7% +2.3% 52%
20 – 39 Low 102 +6.5% −2.9% +3.2% +3.3% 46%
Overall 1,676 +6.5% +2.6% +3.9% +2.6% 56%
Note on the 20–39 tier: The average return (+6.5%) is skewed by a handful of micro-cap stocks that occasionally 3–10× from very low bases. The median is −2.9%, meaning most low-score signals lose money. Low-score signals are high-variance, not a free lunch.

Methodology: Returns are equal-weighted — each signal counts once regardless of company size. Benchmark (XIU.TO) return is measured over the identical 90-day window as each signal, so macro periods (e.g. 2020 crash, 2022 rate cycle) affect signal and benchmark equally. Delisted companies are included where price data was available at the time; excluded where it was not (disclosed omission, not survivorship bias in the traditional sense). No transaction costs or slippage assumed. Past performance is not indicative of future results. This is not investment advice.

Confluence: Consistency vs. Magnitude

Confluence signals (insider buying + active lobbying in the same 90-day window) are more consistent than pure insider-only signals — but the highest-return outliers tend to come from insider-only names.

Signal Type Signals Avg Return Hit Rate Median
Confluence Insider + Lobbying 883 +6.2% 60% +3.5%
Standard Insider only 792 +7.0% 52% +1.0%

Confluence is a consistency filter, not a magnitude amplifier. A 60% hit rate with a +3.5% median means fewer surprises — suitable for systematic positioning. Insider-only signals carry more variance: when they work, they tend to work bigger; when they fail, the drawdown is steeper. The Confluence badge on the leaderboard flags the more reliable cohort.

Key Finding: Fewer Buyers = Better Returns
Avg 90-Day Return by Number of Unique Insiders Buying  ·  Hover bars for detail
0% 3% 6% 9% 12% 1 unique buyer ▸ Avg 90-day return: +11.3% · The highest-conviction pattern in the model +11.3% 1 buyer lone conviction 2–4 unique buyers ▸ Avg 90-day return: +7.8% · Small cluster, still meaningful +7.8% 2–4 buyers small cluster 5–19 unique buyers ▸ Avg 90-day return: +4.2% · Diluted signal, possible plan participation +4.2% 5–19 buyers diluted signal 20+ unique buyers ▸ Avg 90-day return: +2.7% · Likely institutional or DRIP noise — not a signal +2.7% 20+ buyers noise

The single strongest predictor in the model is the number of unique insiders buying. One insider buying alone is far more predictive than a crowd of 20 buying simultaneously. Large-cap, high-volume insider patterns (banks, pipelines) are mostly noise.

Unique Buyers Avg 90-Day Return Interpretation
1 +11.3% Lone insider with conviction — highest signal
2 – 4 +7.8% Small cluster, still meaningful
5 – 19 +4.2% Diluted signal, possible plan participation
20+ +2.7% Likely institutional or DRIP noise
Score Components (0 – 100 pts)
Component Max Points Logic
Conviction 30 1 unique buyer = 30 pts  ·  2–4 = 22 pts  ·  5–9 = 15 pts  ·  10–19 = 8 pts  ·  20+ = 3 pts
Buy/Sell Ratio 20 Ratio of buy value to sell value × 20. Pure buying = 20 pts.
Dollar Value 25 $1M–$10M = 25 pts (sweet spot)  ·  $100K–$1M = 20 pts  ·  $10M–$50M = 15 pts  ·  $50M+ = 8 pts  ·  <$100K = 5 pts
Lobbying Sweet Spot 15 51–200 active regs = 15 pts (engaged, not ubiquitous)  ·  11–50 = 12 pts  ·  1–10 = 10 pts  ·  200+ = 5 pts (mega-lobbyists are noise)
Contract Wins 10 $10M+ federal or provincial contracts = 10 pts  ·  $1M+ = 7 pts  ·  3+ wins = 4 pts  ·  1+ win = 2 pts
Private Placement Conviction 8 Credible investors writing cheques in a private placement is pre-public conviction. $1M+ deal = 8 pts  ·  $100K+ = 6 pts  ·  any deal = 4 pts. Sourced from Globe Newswire press releases and SEDI acquisition filings.
Insider Track Record 10 Credibility score of buying insiders based on their historical trade accuracy. ≥70% credibility = 10 pts  ·  ≥50% = 6 pts  ·  ≥30% = 3 pts
Confluence Bonus 10 Any three or more of: insider buying, active lobbying, contract wins, private placement in the same 90-day window = 10 pts. Any two = 5 pts. The core thesis: when all signals align, the edge compounds.
Velocity & Reversal Bonuses up to +18 Velocity: buying accelerating vs prior 90-day window (+10 pts max). Reversal: buying after a prior sell pattern (+8 pts max). Applied as adjustments — not stored as separate DB columns.

Component totals can exceed 100 before bonuses — the final score is capped at 100. A signal scoring 100 has maxed the conviction, value, and confluence components with velocity or reversal confirmation on top.

Data Sources
Insider Trading

SEDI (System for Electronic Disclosure by Insiders)

Canadian Securities Administrators. All TSX & TSXV companies. 113,000+ transactions from 2020 to present.

Federal Lobbying

Office of the Commissioner of Lobbying (OCL)

171,000+ registrations from 1996 to present. Matched to TSX tickers by company name.

Federal Contracts

Federal procurement databases

1.26M+ federal contracts. 41,300 matched to TSX issuers.

Provincial Contracts

QC, ON, BC, AB, NS open data portals

622,000+ provincial contracts. 8,495 matched to TSX issuers. Paid tier only.

Private Placements

Globe Newswire press releases & SEDI acquisition filings

PP announcements detected via newswire RSS feeds and SEDI transaction code 75 (exempt-market acquisitions). Deal size, price, and warrant coverage extracted where available. Coverage is growing as the parser matures.

Live Track Record
Closed Signals
316
306 tradable
Hit Rate
65%
Avg 90d Return
+11.3%
median +7.9%
Alpha vs XIU.TO
+5.1%
median +1.4%

Every signal generated since January 2025 is tracked in real time at /track-record — individual named signals with actual TSX entry prices, 90-day exit prices, and benchmark comparison against XIU.TO over the identical window. Returns are verifiable against any TSX data source.

Closed signals (90-day window elapsed) show confirmed returns. No cherry-picking — every signal with score ≥ 40, one per ticker per month. 12 of 661 signals are quarantined for data-quality reasons before any statistic is computed. Headline figures use the tradable-universe weighting (entry price ≥ $1.00); a sizable share of the alpha is concentrated in mining-sector and less-liquid names — see the full methodology & validation breakdown for weighting schemes, sector attribution, and score-bucket statistics.

See Pricing Live Track Record View Leaderboard
Form55 provides data and analysis for informational purposes only. Nothing on this site constitutes investment advice or a recommendation to buy or sell any security. Past performance is not indicative of future results.