Category Archives: Sentiment Simulation

TQQQ trading strategy result

TQQQ Trading Strategy using SignalSolver Sentiment

Posted on by

TQQQ Trading Strategy using SignalSolver Sentiment

This TQQQ trading strategy using SignalSolver Sentiment gave 213% annualized return for the period Jan 4th 2021 to June 2nd 2022. The sentiment threshold was set to 50% for the entire period.

Sentiment run for TQQQ showing 213% Annualized Return

TQQQ Sentiment Run showing 213% Annualized Return. Notice good symmetry and structure on the Threshold Surface.

Settings are shown below:

Settings Tab settings

Settings Tab

Notice that only OHLC prices and short period (10 day) SMAs and EMAs are used in the backtests.

Below are shown the Report Tab settings, notably 240 days of data were used for the backtests, and only percentage band was used (PB).  As with all Sentiment runs, out-of-sample walk-forward simulation is used. Sentiment is determined for a particular day by using the backtester on prior data, using the top 5 algorithms' long or short state. If the sentiment crosses the 50% threshold in either direction, a trade is performed appropriately.

Report Tab Settings.

Report Tab Settings.

Result tracking for SignalSolver Sentiment

Updates to SignalSolver Sentiment Results

Posted on by

Updates to SignalSolver Sentiment Results

Daily updates of Sentiment for selected symbols

Final Update

The Feb 6th update will be the final one. While the algorithms gave encouraging initial results (annualized returns averaging around 27%), they began to reduce around Nov 2021. In the coming weeks, I will publish the results for the individual constituents on the pages referenced below and also take a look at what could be done differently to improve the longevity of the systems.

Daily updates to the SignalSolver Sentiment results

The %returns shown are the result of actual trading these securities using the SignalSolver Sentiment technique. They are not a backtest result. While backtesting was used to determine the parameters of the algorithms prior to July 16th 2021, since then we have been walking forward with out-of-sample data trading using those parameters. The returns are exactly what any trader would have realized by following the method from July 16th 2021, assuming the published opening prices could have been attained in practice. Also we have not changed the portfolio members subsequent to July 16th.

How we trade

These updates are posted before the market open (the time at which all trades are made) so that you can trade along with us if you wish. Tickers which have just changed sentiment will show as "Turned" and will be need to be traded appropriately at the next open following the date shown. Other tickers ( designated "Bullish" or "Bearish") do not need to be traded as they are already in the appropriate hold state, long or short. We hold long if bullish and short if bearish for each security. We show the equity value from a fixed date, currently July 16th 2021, the date we started actual trading this particular basket of symbols. Note that the July 16th  equity values are not very meaningful because they derive from backtests, but the percentage change in equity to the present is meaningful. The equity curves can be found in the postings:

AAPL, TQQQ, FNGU, SOXL, SQQQ, TECL, FAS, GUSH

Ticker Date: Sentiment Jul-16-2021 Current Return
AAPL 2/4/22:  Bullish $32,323 $28,307 -12.4%
TQQQ 2/4/22:  Bullish $98,781 $64,280 -34.9%
FNGU 2/4/22:  Bullish $444,937 $360,602 -19.0%
SOXL 2/4/22:  Bullish $43,184 $41,468 -4.0%
SQQQ 2/4/22:  Bearish $39,752 $31,459 -20.9%
TECL 2/4/22:  Bullish $36,013 $31,339 -13.0%
FAS 2/4/22:  Bearish $38,983 $37,649 -3.4%
GUSH 2/4/22:  Bullish $100,476 $84,337 -16.1%
Average: -15.5%

TECL Trading Strategy Using SignalSolver Sentiment

Posted on by

TECL trading using SignalSolver Sentiment

A sentiment driven trading strategy with adaptive thresholds

Methodology

Sentiment is usually based on a consensus of opinions of expert humans, however SignalSolver sentiment is the consensus opinion of multiple backtest algorithms. In the same vein as the previous few posts, this is a TECL trading strategy using SignalSolver sentiment using an adaptive threshold. For a full explanation of the SignalSolver sentiment methodology and how to interpret the simulation results, please click here.

TECL Equity curve using adaptive threshold

TECL Equity curve using adaptive threshold

The adaptive threshold technique examines the thresholds surface every 5 trading days (configurable) and re-optimizes the thresholds accordingly. The threshold is currently at 25% but this could change as we move forward. The buy and sell thresholds are constrained to be equal for TECL.

Performance

TECL trading strategy performance, using adaptive threshold

TECL trading strategy performance, using adaptive threshold

The TECL trading strategy using SignalSolver sentiment (L&S column above) has performed just under 2 times better in this simulation than buy-hold in terms of reward/risk,total return, and (CAGR). Drawdown has been around the same as for buy-hold. Just to re-iterate--this is not a backtest result, it is a walk-forward simulation using out-of-sample trading prices.

Below are the threshold surface for the entire window of 7/16/20 through 8/13/21, showing good structure both for the buy=sell constraint, and the entire surface.  Note the peak is at $34,789.

TECL partial threshold surface for equal buy-sell, with a peak currently centered on 25%

Above: TECL partial threshold surface for equal buy-sell with a peak currently centered on 25%

TECL entire threshold surface for the current sentiment profile

Above: TECL entire threshold surface for the current sentiment profile

Click here to see the SignalSolver settings for this strategy: TECL Sentiment Settings

We now move into the paper-trading phase for this project. Updates will be shown below.

Updates

Updates to this strategy and current sentiment can be found here.

FNGU Trading using SignalSolver Sentiment

Posted on by

FNGU trading using SignalSolver Sentiment

Using multiple algorithms to drive trading strategy

Original Post July 27 2021

Sentiment

Sentiment usually refers to an analyst opinion on whether a financial instrument will increase in value (bullish sentiment), or decrease (bearish sentiment). However, in this FNGU trading strategy using SignalSolver sentiment we are combining the opinion of multiple backtest algorithms to derive sentiment.

Methodology

Shown above is the simulated result of trading FNGU using SignalSolver Sentiment. The sentiment is the blue area chart in the background. The equity curve for the strategy is shown in yellow, buy-hold equity in white. Sentiment is calculated each day after the close of business by assessing what percentage of the top 10 SignalSolver backtest algorithms are bullish. The top 10 are selected by sorting the 139 algorithms each day according to performance. The buy and sell thresholds are fixed at 50% (red line) with bullish being above the threshold. A trade is executed at the next open whenever sentiment crosses this threshold, so the trade price is always out-of-sample from the backtest period which is fixed at 250 trading days. The simulation then walks forward to the next day, repetitively. Algorithms are flushed and refreshed every 3 months and re-parameterized at the end of each month

Performance

Trading on sentiment (L&S column above) performed around nine times better in this simulation than buy-hold in terms of reward/risk, with annualized return (CAGR) being around 6 times better for Long/Short trading of the signals and trading long only being about 5 times as good. In all cases, drawdown was lower for the sentiment trading than for buy-hold.

Below is shown the threshold surface for the equal buy/sell thresholds showing that annualized return (CAGR) is sensitive to threshold changes but profitable over a wide range. 50% is close to the optimum, which is at 41% through 49% ($580,959 return).

FNGU threshold surface for equal thresholds

FNGU threshold surface for equal thresholds

 

 

 

Click here to see the SignalSolver settings for this strategy: FNGU Sentiment Settings

We now move into the paper-trading phase for this project. Updates will be shown below.

Updates

Daily updates to this strategy and sentiment were reported here, up until Feb 4th 2022 when losses on FNGU were about 19%. The screenshot below shows the progress of this algorithm.  The underlying stock lost 23% in the same period.

FNGU algorithm using SignalSolver sentiment. Performance up until Feb 4th 2022

FNGU trading using SignalSolver Sentiment. From Jan 8th 2020 until July 16th 2021 this was a backtest. From July 16th 2021 until Feb 4th 2022 it was live traded, losing 19%.

Postmortem March 3rd 2022

As we did for AAPL and TQQQ we take a look to see if something could have been done better. We start by using the same Sentiment profile and looking to see if changing the buy and sell thresholds would have made a difference. For FNGU we used a fixed 50-50 threshold because it had done such a great job in the timeframe 1/8/20 to 7/16/21. Turns out, the best Equal threshold overall (i.e. from 1/8/20)  would have been 60%, but that was not guessable, not manifesting until Dec 2021. Trading from 1/8/20 with a 60% threshold would have yielded just over $900,000 in Dec 2022, falling back to $576,000 on Feb 4th 2022. For our live trading period, it would have yielded just 56%. The best Equal threshold for our trading period July 16th 2021 to Jan 4th 2022 was also 60%.

The best Symmetrical thresholds were 75% buy and 25% sell, yielding 100% profit in our trading period. Another academic result, neither guessable nor manifesting themselves until very recently.

Adaptive threshold results

We found with both AAPL and TQQQ that adaptive thresholds can give better results than fixed thresholds, so let's explore that technique a little for FNGU. With this method there is less guesswork--the program optimizes the thresholds every N periods, but you must also select how much sentiment data is in the Optimization Window. For simplicity sake we optimize every 1 period (every trading day) and we use a 252 trading day window (one calendar year).  You can also force the thresholds to be Equal, Symmetrical, or allow them to float freely. Each did much better than buy-hold for the trading period which gave a 24% loss. Let's take a look at each

Equal Adaptive Thresholds

For this test the buy and sell thresholds are constrained to be equal. Overall it did better than buy-hold, but for the actual trading period (July 16th to Jan 4th '22) it gave a loss of 4%, recovering to flat since then.

FNGU adaptive thresholds-equal thresholds

Symmetrical Adaptive Thresholds

Here, we apply two constraints to the thresholds. Firstly they must sum to 100% and secondly the buy threshold must be greater or equal to the sell threshold. For the overall test period this gave the best result, and for the trading period 7/16/21 through to 2/4/22 this gave a 13.9% profit, but this has declined to a 3% loss on 3/2/22.

FNCU adaptive threshold, symmetrical thresholds

Free floating adaptive thresholds

The thresholds are re-optimized every day with the only constraint being that the buy threshold must be greater or equal to the sell threshold. This avoids the scenario where a descending sentiment causes a sell, then re-ascends without a buy (relaxing this constraint was still profitable). The result is better for the trading period 7/16/21 to 2/4/22 than either the equal or symmetrical thresholds, giving a return of 57%.. As of 3/2/22 the gain was 65% vs a 36% loss for buy-hold.

FNGU adaptive threshold, free floating