When Is Fresh AI Stock Analysis Worth It? Allocating a Limited Research Budget Across Price Updates, Deep Forecast Refreshes, and Editorial Reviews of Top Stock Picks
Authors: Russlan Ramdowar
Organizations: Future Edge Group FZE, United Arab Emirates
When is another AI research run worth more than keeping that money invested? Using 8,120 iPulse AI reports that consumed nearly 100 million output and reasoning tokens on the same 203 stocks across four production batches, we compare repricing old targets (with and without shock safeguards), mechanical growth-path resets and fresh multi-agent reports. Ten matched configurations represent seven investment frameworks. The primary economic test selects equal-weight Top 10 USD portfolios from one-year forecasts, net of 10 bps trading costs and a USD 3,000 all-in charge for fresh research on a USD 300,000 account. In two unchanged-model short windows, guarded reuse averages 2.25%, versus 1.66% for SPY and 4.24% for fresh reports. Guarded reuse beats SPY in all three short windows. Extending the first holding window to 176 days reverses the comparison: guarded reuse returns -11.26%, fresh reports +8.55%, and SPY +3.46%, motivating the thesis half-life question. Supporting quarter-forecast diagnostics show that mechanically resetting old growth paths closes 98% of the MAE gap to fresh reports, yet Fresh and Reset share only 1-4 Top 10 stocks. Top 30 reverses the unchanged-model comparison in favor of guarded reuse (4.17% versus 1.37%). Concentration tests expose dependence on exceptional winners. Nine editorial editions show substantial between-edition turnover, but each final screen retains its own incoming list. Recurring budget scenarios retain initial holdings: monthly costs approach realized short-window refresh value, while weekly budgets require larger additional gains. A matched ranking-continuity extension extracts further value from retained forecasts without eliminating thesis ageing. The architecture separates continuous price monitoring, episodic thesis rebuilding and evidence-based editorial checks.
Figures & tables
Figure 1: Experimental overview. Across a fixed panel of 203 stocks, we compare price-updated old targets (with and without a price-shock safeguard), mechanically reset growth paths, and fresh multi-agent reports. Our primary economic test evaluates one-year signals in Top 10 USD buy-and-hold portfolios against SPY net of modeled trading and compute costs (with Top 30 as a breadth sensitivity). Completed-quarter forecast accuracy and a nine-edition editorial audit provide supporting evidence.
Batch
All assets
Stocks
Reports
Role here
3
247
218
2,718
Old paths for first transition
4
312
283
3,434
First fresh-quarter comparison
5
312
283
3,736
Evolving-system comparison
6
377
348
4,523
Second same-model comparison
7
426
383
5,964
Editorial audit; quarter pending
Table 1: Historical production coverage across Batches 3–7 prior to balanced-panel matching.
Figure 2: Mechanics of forecast reuse. When the observed price at entry t (110) exceeds the old path’s interim prediction (105), fixed-target repricing retains the 120 target and compresses remaining upside to 9.09%, whereas a shape-preserving reset shifts the implied terminal target to 125.71 (+14.29%). A fresh report can revise both the target level and the trajectory using updated evidence.
Window
Old fixed
Old + guard
Path reset
Fresh
SPY
3 → 4 ( 3mo)
3.02%
2.44%
2.72%
4.55%
1.36%
4 → 5 ( 3mo)
4.45%
4.59%
22.92%
22.45%
4.47%
5 → 6 ( 3mo)
2.06%
2.06%
6.57%
3.93%
1.97%
Same-model mean
2.54%
2.25%
4.65%
4.24%
1.66%
3 → 4 ( 6mo)
-6.15%
-11.26%
-3.98%
8.55%
3.46%
Table 2: Top 10 buy-and-hold portfolio returns (USD), including all four signal arms and SPY, after 10 bps per-leg fees and a USD 3,000 upfront operating charge on Fresh and USD 300,000 starting capital.
Figure 3: Top 10 portfolio excess returns (in percentage points) relative to SPY over identical holding windows net of modeled costs. Guarded old targets outperform SPY across all three 3-month windows without new LLM inference, but suffer a sharp reversal when held unrefreshed for six months (May–Oct).
Figure 4: Concentration stress test for Fresh Top 10 portfolios. Each bar group compares the baseline Fresh Top 10 return against the same portfolio with its single best-performing stock slot left in cash (retaining full upfront research charges) and against SPY.
Transition
Reuse raw
Reuse 75/25
Fresh raw
Fresh 75/25
SPY
3 → 4
3.72
3.46
4.55
4.83
1.36
4 → 5
7.42
27.16
25.86
26.97
4.47
5 → 6
6.19
8.91
6.75
6.75
1.97
3 → 4 (long)
-1.57
-4.23
8.55
38.36
3.46
Table 3: Matched Top 10 net holding-period returns (%). USD300,000, 10 bps per actual share trade on entry and exit, USD3,000 incremental research bill on fresh arms, configured net realized dividends and earned receivables. The first three rows are short windows; the last holds the first selections longer. These returns are neither annualized nor compounded across rows.
Method
Same-model MAE
RMSE
Evolving MAE
RMSE
Fixed-target repricing
15.257
22.708
15.431
23.552
Shape-preserving reset
13.548
19.428
13.519
20.489
Fresh deep reports
13.507
19.583
13.438
20.301
No-change forecast
13.746
–
13.739
–
Table 4: Council first-quarter price-return forecast errors in percentage points. The same-model and evolving series contain 406 and 609 cases on the same 203 stocks.
Figure 5: First-quarter council forecast error across the 203-stock panel. Panel A: Mean Absolute Error (MAE) in percentage points across the same-model (406 cases) and evolving-system (609 cases) series. Panel B: Paired Fresh-minus-Reset MAE differences with 95% whole-stock bootstrap percentile intervals. Negative values indicate lower error for fresh reports.
New batch
Input M
Output M
Standard USD
Batch USD
Mean council USD
4
147.31
25.25
473.87
243.81
2.33
5
125.53
23.70
487.22
246.29
2.40
6
138.55
23.18
525.17
264.26
2.59
Total / mean
411.38
72.13
1486.27
754.36
2.44
Table 5: Measured successful-report tokens and normalized API reference charges for each 203-stock, ten-report refresh. These figures are retained separately from the all-in operating scenario.
Transition
Capital USD
Research USD
Guarded reuse
Fresh
3 → 4
10,000
3000.00
2.44%
-26.07%
3 → 4
100,000
3000.00
2.44%
2.44%
3 → 4
300,000
3000.00
2.44%
4.55%
3 → 4
1,000,000
3000.00
2.44%
5.29%
5 → 6
10,000
3000.00
2.06%
-26.52%
5 → 6
100,000
3000.00
2.06%
1.83%
Table 6: Capital-sharing sensitivity for one USD 3,000 full-cycle charge. Trading fees remain 10 bps per leg; the same selections and realized market outcomes are retained.
Window
Budget cadence
Runs
Budget USD
Capital
Fresh held
Reuse
05-07–07-30
Weekly
12
36,000
12%
-7.06%
+2.44%
05-07–07-30
Monthly
3
9,000
3%
+2.44%
+2.44%
06-09–09-04
Weekly
13
39,000
13%
+7.61%
+4.59%
06-09–09-04
Monthly
3
9,000
3%
+19.98%
+4.59%
07-07–09-30
Weekly
13
39,000
13%
-8.67%
+2.06%
07-07–09-30
Monthly
3
9,000
3%
+1.83%
+2.06%
Table 7: Weekly and monthly research-budget sensitivity on USD 300,000. “Fresh held” retains the initial fresh-selected stocks after reserving the full scheduled budget. Reuse pays no new inference charge. These are fixed-selection cost scenarios, not observed recurring-refresh strategies.
Figure 6: The cost hurdle of recurring research. Panel A shows weekly and monthly full-run budgets across the actual holding windows. Panel B deducts those reserved budgets while holding the initial Fresh Top 10 selection fixed; diamonds show guarded reuse. Additional reruns must improve decisions enough to overcome this hurdle.
Edition (UTC date)
Batch
New vs prior
Screen replaced
2026-08-27
6
–
0
2026-09-07
6
2/10
0
2026-09-21
7
8/10
0
2026-10-01
7
4/10
0
2026-10-05
7
4/10
0
2026-10-12
7
2/10
0
Table 8: New stocks relative to the preceding published edition versus replacements by that edition’s final screen. Ten candidates were recorded in each edition.
Figure 7: Published-pick turnover versus final editorial validation. Panel A shows new stocks in successive published editions; Panel B shows that each final screen retains its own incoming ten candidates. These are distinct comparisons.
Appendix figures & tables9 assets
Supplementary material from the paper’s appendix.
Appendix
Series (cases)
Δ MAE (pp)
95% stock-cluster interval
Fresh wins
Same model (406)
-0.040
[-0.380, +0.289]
49.5%
Evolving (609)
-0.081
[-0.386, +0.244]
51.9%
3 → 4 (203)
-0.419
[-0.958, +0.109]
52.2%
4 → 5 (203)
-0.161
[-0.779, +0.504]
56.7%
5 → 6 (203)
+0.339
[-0.126, +0.790]
46.8%
Appendix
Table 9: Paired Fresh-minus-Reset first-quarter MAE differences, stock-cluster intervals and fresh win shares.
Transition
Rank correlation
Shared Top 10
Shared Top 30
3 → 4
0.609
1/10
12/30
4 → 5
0.591
4/10
15/30
5 → 6
0.733
4/10
9/30
Appendix
Table 10: Cross-sectional rank correlation and shared membership between Fresh and Reset quarter-ranked shortlists.
Figure 8: Shortlist overlap between Fresh reports and Old-path reset for Top 10 (left) and Top 30 (right) selections ranked by predicted first-quarter return.
Transition
Stocks chosen
Old targets
Old paths reset
Fresh reports
3 → 4
10
5.20%
10.89%
5.13%
3 → 4
30
4.55%
1.09%
5.63%
4 → 5
10
2.14%
19.27%
20.68%
4 → 5
30
0.85%
10.22%
9.19%
5 → 6
10
7.69%
16.85%
4.83%
5 → 6
30
5.48%
1.87%
6.37%
Appendix
Table 11: Subsequent equal-weight native-quarter quote-currency price returns, before dividends, FX and fees. Column order is Old targets, Reset, Fresh.
Figure 9: Subsequent equal-weight native-quarter price returns for Top 10 (left) and Top 30 (right) quarter-ranked shortlists.
Selection rule
Old targets
Old paths reset
Fresh reports
Top 10: six-month forecasts
-2.47%
8.10%
-1.07%
Top 30: six-month forecasts
1.91%
-1.32%
3.40%
Top 10: original quarter picks
-8.25%
9.01%
-1.09%
Top 30: original quarter picks
1.34%
2.15%
5.23%
Appendix
Table 12: Nearly six-month quote-currency price-return sensitivity for the first transition through 30 October 2026.
Series
Convention
Δ MAE (pp)
95% interval
Same model
Geometric (primary)
-0.040
[-0.380, +0.289]
Same model
Linear interpolation
-0.042
[-0.380, +0.286]
Same model
Realization-date expiry
-0.041
[-0.379, +0.287]
Evolving
Geometric (primary)
-0.081
[-0.386, +0.244]
Evolving
Linear interpolation
-0.082
[-0.387, +0.242]
Evolving
Realization-date expiry
-0.081
[-0.385, +0.242]
Appendix
Table 13: Fresh-minus-Reset MAE under alternative interpolation and realization-date conventions.
Window
Old fixed
Old + guard
Path reset
Fresh
SPY
3 → 4 ( 3mo)
6.75%
5.70%
1.62%
5.39%
1.36%
4 → 5 ( 3mo)
8.77%
7.61%
9.47%
11.44%
4.47%
5 → 6 ( 3mo)
5.48%
2.64%
2.41%
-2.66%
1.97%
Same-model mean
6.12%
4.17%
2.01%
1.37%
1.66%
3 → 4 ( 6mo)
3.24%
5.71%
-1.27%
16.86%
3.46%
Appendix
Table 14: Top 30 buy-and-hold portfolio returns (USD) under the same fee and all-in operating-cost assumptions as Table 2 .
Window
Top k
Common: old + guard
Common: fresh
Common: both guarded
3 → 4 ( 3mo)
10
2.44%
4.55%
4.55%
3 → 4 ( 3mo)
30
5.13%
5.39%
4.60%
4 → 5 ( 3mo)
10
-0.69%
22.45%
22.45%
4 → 5 ( 3mo)
30
7.46%
11.44%
11.44%
5 → 6 ( 3mo)
10
2.07%
3.93%
3.93%
5 → 6 ( 3mo)
30
2.64%
-0.36%
-0.36%
Appendix
Table 15: Common 365-day endpoint and symmetric-safeguard portfolio returns after modeled costs.
Financial forecasting uses market, company, and economic data to predict prices, returns, volatility, and business outcomes for decisions and risk management.