We built 19 Borsa Istanbul research systems but still cannot prove a real trading edge — what are we missing?

[sedatguner2000-coder]

We have been developing an independent decision-support system for Borsa Istanbul for approximately 22 months.

The system uses only delayed market information that was available at the exact decision time. It does not use future data, real-time private feeds, other stock markets, or automated order execution. It does not manage client money. Its purpose is to examine the market, identify candidates, compare their relative strength and risk, and produce a manual daily decision.

How the system works

Over time, we built and tested 19 different research architectures. These were not simple parameter changes; they examined different combinations of price behaviour, intraday movement, market and sector conditions, historical similarities, candidate ranking, downside protection, capital allocation, holding periods, and exit decisions.

The current AVCI architecture contains:

• 20 main modules
• 23 supporting files
• Data collection and validation
• Decision-time locking
• Market and sector analysis
• Proprietary pattern and similarity layers
• Candidate-pool creation
• Candidate filtering and ranking
• Risk and uncertainty checks
• Decision recording
• Next-session result and cost measurement
• Final consistency and evidence checks

Historical daily and real one-minute BIST price and trading data have also been examined. Information created after the decision time is not supposed to enter the decision process.

The unresolved problem

Despite thousands of hypotheses, simulations, tests, and several complete architecture changes, we have not been able to prove a repeatable and executable after-cost edge.

Promising historical results often weaken or disappear when:

• The market period changes
• Transaction costs are included
• Capital is distributed among candidates
• Holding and replacement rules change
• Large winning days or stocks are removed
• Previously unused periods are tested
• Realistic execution assumptions are applied

A further problem is that much of the historical period has already been examined during research. After thousands of experiments, even an apparently excellent historical result may simply be a false discovery caused by overfitting and repeated testing.

There are also unresolved differences between a paper result and actual capital growth. A correct candidate does not automatically mean a profitable trade. Entry price, liquidity, slippage, tradable quantity, transaction costs, corporate actions, holding time, and exit timing can all change the result.

Our historical records also do not provide a complete real-money ledger containing every decision, executed quantity, entry, exit, cost, and daily capital change. For this reason, some old results cannot be reconstructed as genuine executable performance.

At present, we cannot confidently distinguish between three possibilities:

1. Delayed BIST information may contain no persistent edge strong enough to survive all costs.
2. A real edge may exist, but it may be lost during ranking, allocation, holding, replacement, or risk control.
3. The apparent edge may exist only on paper because execution and historical validation assumptions are unrealistic.

What we are looking for

We are not looking for:

• Stock tips
• A ready-made strategy
• Another generic machine-learning model
• Hundreds of new indicators
• A twentieth architecture built without first identifying the real problem

We are looking for experienced researchers, graduate students, quantitative developers, market-microstructure specialists, or independent practitioners who are willing to examine this problem carefully and patiently.

The central question is:

What immutable and pre-registered test could determine whether AVCI contains a real, executable and persistent after-cost edge—or whether the apparent historical advantage is only the result of overfitting, repeated testing, or unrealistic execution assumptions?

We are especially interested in people with experience in:

• Backtest overfitting and false discovery
• Delayed financial data
• Emerging or relatively illiquid equity markets
• Borsa Istanbul
• Transaction costs, liquidity and slippage
• Portfolio allocation and risk
• Holding and replacement decisions
• Walk-forward or prospective testing
• Pre-registration and independent validation

A negative conclusion is acceptable. The objective is not to make an unsuccessful system appear successful. The objective is to determine, with defensible evidence, whether a real edge exists, where it disappears, or why it cannot be extracted under the current constraints.

This is not a quick question that can be solved with one indicator or a few comments. We are looking for serious contributors who are willing to understand the architecture and help define a small number of decisive experiments.

A concise anonymized technical summary can first be shared with serious contributors. Proprietary selection rules, the complete source code, and raw data that we do not have the right to redistribute will not be posted publicly.

Our core question is:

Why, although this large research infrastructure appears able to identify strong candidates, can we not convert that ability into repeatable, executable, after-cost capital growth across different market periods?

[Kxrma47]

Your description already identifies the central statistical problem: after thousands of adaptive experiments, the historical record is training data for the research process, even when a particular model did not directly fit every observation. No resampling of that same history can recreate a truly untouched test.

The cleanest decisive experiment is therefore a pre-registered prospective shadow portfolio.

Before the start date, freeze and hash:

• the complete code/container and data-vendor/version;
• universe and survivorship/corporate-action rules;
• decision timestamp and data-availability lag;
• candidate ranking, allocation, replacement and exit rules;
• maximum participation, order type, fill model, fees, taxes and slippage;
• capital, position limits and handling of unfilled/partial orders;
• one primary after-cost metric, benchmark and failure threshold;
• duration/sample-size rule and all permitted reasons for stopping.

Publish the hash and protocol before observing the period. Each day, append an immutable decision record before the execution window: eligible universe, inputs available at that timestamp, desired orders, quantities, rejected candidates and reason codes. Then record actual or independently simulated fills using auditable bid/ask/volume data. Do not modify the frozen system; log proposed improvements for a later experiment.

The primary result should be portfolio-level after-cost return relative to a predeclared implementable benchmark, with drawdown and turnover constraints. Report the full equity curve and every order, not only selected candidates or “correct calls”. Use block/bootstrap or HAC-aware uncertainty for dependent returns, but do not turn repeated interim looks into new hypothesis tests.

To locate where edge disappears, freeze a small attribution ladder in advance:

1. raw candidate return at the decision timestamp;
2. return after entry delay and executable prices;
3. after liquidity/size limits;
4. after allocation/replacement rules;
5. after all fees, taxes and slippage.

This decomposes signal quality from implementation shortfall without launching another architecture search.

If a prospective test is impossible, the next-best option is a genuinely sequestered dataset controlled by an independent person who returns only the final registered metrics once. But given how extensively the history has been examined, ordinary walk-forward CV is useful for engineering diagnostics—not convincing final evidence of discovery.

Predefine what would count as “no evidence of edge”. A negative prospective result is informative and prevents the twentieth architecture from being selected on the same contaminated history.

Also note that no single test proves persistence indefinitely. It can establish that one frozen decision process survived one genuinely untouched, executable period with a quantified uncertainty and cost model. Replication across a later period is what strengthens the persistence claim.