Key Opinion Leader (KOL) discourse on social media is widely consumed as investment guidance, yet turning it into executable trading strategies without injecting assumptions about unspecified execution decisions remains an open problem. We observe that the gaps in KOL statements are not random deficiencies but a structured separation: KOLs express directional intent (what to buy or sell and why) while leaving execution decisions (when, how much, how long) systematically unspecified. Building on this observation, we propose an intent-preserving policy completion framework that treats KOL discourse as a partial trading policy and uses offline reinforcement learning to complete the missing execution decisions around the KOL-expressed intent. Experiments on multimodal KOL discourse from YouTube and X (2022-2025) show that KICL achieves the best return and Sharpe ratio on both platforms while maintaining zero unsupported entries and zero directional reversals, and ablations confirm that the full framework yields an 18.9% return improvement over the KOL-aligned baseline.
Figures & tables
Figure 1. Representative KOL discourse examples with local price context. KOL statements specify asset-level directional intent but leave execution decisions under-specified.
Statistic
YouTube
X
Coverage / specificity
Mentioned companies
6,774
3,811
Ticker-explicit ratio
81.61%
79.51%
Directional-expression ratio
79.58%
91.62%
Single-mention ratio
62.06%
39.67%
Execution under-specification
Table 1. Empirical evidence that financial KOL discourse behaves like a partial trading policy on the full dataset (18 YouTube KOLs and 14 X KOLs).
Figure 2. Overview of our intent-preserving policy completion framework. Raw financial KOL discourse is transformed into structured signals and mapped to an intent-aligned baseline action. A signal-conditioned completion policy refines the baseline under active KOL signals and completes missing execution behavior. The final action is mapped to executable portfolio weights.
Figure 3. Overview of KICL. Anchor-aware inputs are mapped to a dual-branch residual policy with regime routing. The chosen residual is fused with the KOL-aligned baseline and filtered by hard constraints to produce the final action.
Metric
Description
Performance Metrics
Return
Cumulative return over the evaluation period
Sharpe
Risk-adjusted return based on daily returns
MDD
Largest peak-to-trough drawdown
WR
Event-level win rate against the executable KOL-aligned baseline
Betrayal Metrics
Table 2. Evaluation metrics used in experiments.
Statistic
YouTube
X
Source scope
KOLs (full / benchmark)
18 / 10
14 / 10
Collection period
Jan 2022 – Mar 2025
Mentioned companies
6,774
3,811
Signal characteristics
Ticker-explicit ratio
81.61%
79.51%
Table 3. Summary statistics of the constructed dataset.
X
YouTube
Performance
Betrayal
Performance
Betrayal
Group
Method
Ret ↑
Sha ↑
MDD ↓
WR ↑
UER ↓
DRR ↓
BD ↓
Ret ↑
Sha ↑
MDD ↓
WR ↑
UER ↓
DRR ↓
BD ↓
Heuristic
RMB
0.02
0.30
0.33
0.70
0.00
0.00
0.00
0.27
2.52
0.16
0.50
0.00
0.00
0.00
HAP
0.00
-0.07
0.11
0.70
0.19
0.19
0.02
0.12
2.43
0.07
0.30
0.35
0.12
0.04
Imit./Sup.
BC ( Bain and Sammut, 1995 )
0.01
-0.02
0.11
0.80
0.22
0.19
0.02
0.09
1.94
0.07
0.30
0.27
0.24
0.04
SUP-DELTA
0.02
0.30
0.32
0.40
0.00
0.00
0.01
0.29
2.47
0.16
0.70
0.00
0.00
0.01
Table 4. Main benchmark results on the selected 20-KOL subset under the upgraded event-conditioned benchmark. Methods are grouped by family. Best values are shown in bold and second-best values are underlined within each platform.
Figure 4. Scaled betrayal-form profiles on X and YouTube.
Figure 5. Hard-betrayal probability under excess-positive events on X and YouTube.
Variant
Anchor
Policy
RL Comp.
Regime
Hard
Baseline
✓
✓
WO-RL-COMPLETION
✓
✓
✓
WO-REGIME-SPLIT
✓
✓
✓
✓
WO-H
✓
✓
✓
✓
KICL (Full)
✓
✓
✓
✓
✓
Table 5. Component structure of the ablation variants.
Variant
Δ Return
Δ Sharpe
MDD Change
Δ BD
Baseline
–
–
–
–
WO-RL-COMPLETION
-12.2%
-6.1%
+0.3%
+0.0001
WO-REGIME-SPLIT
+6.9%
-4.2%
+1.0%
+0.0083
WO-H
-65.8%
-29.8%
+16.9%
+0.0306
KICL (Full)
+18.9%
+1.1%
+7.1%
+0.0077
Table 6. Event-level ablation results relative to the KOL-aligned baseline.
Figure 6. Progressive ablation relative to the KOL-aligned baseline. WO-H is shown separately as a destructive control. Bars denote Δ Return, Δ Sharpe, and Δ BD.
Figure 7. Hard-scope ablation across train-only, infer-only, train+infer, and no-hard settings.
Case
Date
Base
Ours
Takeaway
FXI (X/Jake, bullish cue)
FXI
2024-12-02
0.0554
0.0938
Higher long exposure
FXI
2024-12-23
0.0000
0.0000
Both close
FXI
2024-12-24
0.1321
0.1558
Higher-weight re-entry
FXI
2024-12-26
0.0000
0.0000
Both close again
TSLA (YT/Maverick, neutral/wait cue)
Table 7. Exposure-path evidence at the FXI and TSLA divergence nodes in Figure 8 . Positive values denote long exposure and zero denotes near-flat allocation.
Figure 8. Representative case comparisons against the KOL-aligned baseline on X and YouTube; red circles mark the divergence nodes.
Appendix figures & tables2 assets
Supplementary material from the paper’s appendix.
Appendix
Figure S1. Daily mark-to-market equity curves on the selected X benchmark subset.
Figure S2. Daily mark-to-market equity curves on the selected YouTube benchmark subset.