By Keel Research Team
Updated October 15, 2026Strategy optimizer
Strategy optimization for crypto trading
Strategy optimization means running one strategy across many settings and comparing the backtests, so you see which settings work and how much the result depends on them. Keel is a strategy builder and backtester for Hyperliquid perpetuals, and a built-in strategy optimizer is coming soon. Today you change a setting, re-run the backtest with fees, slippage and funding, and compare the runs.
Coming soon
Strategy optimizer
A strategy optimizer is coming to Keel. It is not in the product yet.
In Keel today
- Backtest over the dates you choose, with fees, slippage and funding
- Change a setting and re-run; every version and backtest is kept
- Paper trade on live Hyperliquid prices with no money at risk
What it is
Run many settings, then compare
Most strategies have a few settings: a lookback length, an entry threshold, how many coins to hold, how often to rebalance. An optimizer runs the backtest once for every combination you ask for and puts the results side by side. Three lookbacks, three thresholds and two rebalance rules make 18 backtests.
The useful output is the shape of the whole table, not its best row. If most nearby settings make money, the idea probably has an edge. If one setting shines and its neighbours lose, the best row is likely noise that happened to fit the past.
A good optimizer shows every run, including the losing ones, so you can pick a setting from a stable area of the table instead of its single peak.
Why it matters in crypto
Crypto history is short and noisy
Hyperliquid perps have a few years of history at most, and many coins have much less. A handful of big trend months can make one lookback look brilliant. With that little data, testing many settings and keeping the best one is the quickest way to fool yourself.
Costs change the answer too. Faster settings trade more, so fees and slippage take more of the edge, and a position held through funding pays or earns every hour. A comparison that leaves costs out tends to favour the settings that trade the most.
So every setting you compare should be backtested the way it would trade: with fees, slippage and funding, over the same dates.
A real example
One strategy, every setting tested
The strategy library publishes every setting it tested for each strategy. Here is the momentum strategy, sorted by Sharpe ratio.
Momentum lookback / Momentum selection cutoff / Rebalance bufferSharpe after costs
- 30 / 85 / 0.11.19
- 14 / 75 / 0.11.19
- 30 / 75 / 0.11.18
- 14 / 75 / 0.2 (default)1.17
- 30 / 85 / 0.21.14
- 30 / 75 / 0.21.14
- 7 / 75 / 0.11.10
- 7 / 75 / 0.21.10
- 14 / 85 / 0.11.09
- 7 / 60 / 0.11.06
- 7 / 60 / 0.21.05
- 14 / 60 / 0.11.04
- 14 / 85 / 0.21.04
- 14 / 60 / 0.21.01
- 7 / 85 / 0.10.96
- 7 / 85 / 0.20.93
- 30 / 60 / 0.20.88
- 30 / 60 / 0.10.87
Each bar is a full backtest of one setting. Momentum Strategy on Hyperliquid, Hyperliquid, Aug 2024 to Sep 2026, after trading fees, slippage and funding. Past results don't predict future ones.
See Momentum Strategy on Hyperliquid in the libraryIn Keel today
Compare settings by hand today
Each step an optimizer automates, you can do yourself in Keel now.
Change a setting and re-run
Open a strategy, change a lookback or a threshold, and run the backtest again. Every change is saved as a new version and every backtest is kept, so nothing is overwritten.
Real costs in every run
Every backtest charges trading fees and slippage and applies Hyperliquid's hourly funding to open positions, so a setting that trades a lot pays for it.
How the backtest worksCompare runs with an assistant
Connect Claude or ChatGPT and ask it to try a few settings. It runs the backtests on Keel and compares the results side by side, so you see the spread, not just one number.
Connect your assistantStart from a tested strategy
Each library strategy page lists the settings that were tested, including the ones that lost money. Fork one and start from a setting that held up.
Browse the strategy libraryComing soon
Strategy optimizer
A strategy optimizer is coming to Keel. It is not in the product yet. Sign up free and we'll email you when it ships. Your account works today: build a strategy, backtest it and paper trade it while you wait.
FAQ
Common questions
What is a strategy optimizer?
A tool that runs one strategy across many parameter settings and compares the backtests. It tells you which settings worked and how sensitive the result is to each of them.
Does Keel have a strategy optimizer?
Not yet. A strategy optimizer is coming soon, and if you sign up we'll email you when it ships. Today you can change a setting, re-run the backtest and compare the runs yourself or with a connected assistant.
Is optimizing a trading strategy just overfitting?
It can be. The more settings you try, the more likely the best one is luck. Look at the spread of results rather than the top row, prefer settings whose neighbours also work, and check the result on dates you did not use to choose it.
How many settings should I test?
Fewer than you think. A few values per setting around a sensible default tell you most of what you need. Hundreds of combinations on a couple of years of crypto data mostly find noise.
Should I trade the best setting from the table?
Rarely. The best row of any comparison is biased upward because it was picked for being best. Choose a setting from an area where most nearby settings did well, and expect live results to be weaker than that backtest.
How realistic are Keel's backtests?
Every backtest charges trading fees and slippage on each trade and applies Hyperliquid's real hourly funding to every open position. It is still a simulation: fills are modelled, and past results don't predict future ones. How Keel works explains how the backtest and the live run use the same compiled strategy.
Start with a backtest
Sign up free and we'll email you when it ships. Your account works today: build a strategy, backtest it and paper trade it while you wait.