Dynamic Neural RSI Trend Following Trading Strategy

Pine ScriptMachine learning Trend following Mean reversion RSI EMA SMA

Author: ChaoZhang
Complexity: Starter · 58 lines
Parameters: 0
Backtest bar: 15m · intraday
Tested on: BTC/USDT · futures

Jump to code View in vault Original on FMZ

Overview

This strategy is a quantitative trading system based on moving averages, RSI indicator, and trailing stop loss. It combines trend following and momentum indicators from technical analysis, achieving risk-controlled trading through strict entry and exit conditions. The core logic is to seek oversold opportunities in uptrends and protect profits using trailing stops.

Strategy Principles

The strategy uses a 200-day Simple Moving Average (SMA) as the baseline for trend judgment, combined with the Relative Strength Index (RSI) for generating trading signals. Specifically:

Uses 200-day SMA to judge the major trend, only considering long positions when price is above the average
Identifies oversold signals when RSI falls below preset threshold (default 40)
Triggers long entry when both conditions are met and waiting period since last exit (default 10 days) has elapsed
Protects profits during position holding through trailing stop loss (default 5%)
Exits position when price breaks below trailing stop or 200-day SMA

Strategy Advantages

Combines trend and momentum double filtering to improve trading accuracy
Uses trailing stop mechanism to effectively lock in profits
Sets trading intervals to avoid frequent trading
Strong parameter adjustability to adapt to different market environments
Clear trading logic, easy to understand and execute
Simple calculations with high computational efficiency

Strategy Risks

Moving average lag may cause delayed entry and exit signals
RSI indicator may generate false signals in ranging markets
Fixed percentage trailing stop may not suit all market environments
Parameter optimization may lead to overfitting
May suffer significant drawdowns in highly volatile markets

Strategy Optimization Directions

Introduce volatility-adaptive trailing stop percentage
Add volume indicators as auxiliary confirmation
Replace simple moving average with exponential moving average for better sensitivity
Incorporate market sentiment indicators to optimize trading timing
Develop dynamic parameter optimization mechanism
Add multi-timeframe strategy confirmation mechanism

Summary

This is a quantitative trading strategy with complete structure and clear logic. It pursues stable returns while controlling risk by combining multiple technical indicators. Although there is room for optimization, the basic framework has good practicality and extensibility. The strategy is suitable for medium to long-term investors and adapts well to different market environments.

Source Pine Script

/*backtest
start: 2025-01-09 00:00:00
end: 2025-01-16 00:00:00
period: 15m
basePeriod: 15m
exchanges: [{"eid":"Futures_Binance","currency":"BTC_USDT","balance":49999}]
*/

//@version=5
strategy("200 SMA Crossover Strategy", overlay=false)

// Define inputs
smaLength = input.int(200, title="SMA Length")
rsiLength = input.int(14, title="RSI Length")
rsiThreshold = input.float(40, title="RSI Threshold")
trailStopPercent = input.float(5.0, title="Trailing Stop Loss (%)")
waitingPeriod = input.int(10, title="Waiting Period (Days)")

// Calculate 200 SMA
sma200 = ta.sma(close, smaLength)

// Calculate RSI
rsi = ta.rsi(close, rsiLength)

// Plot the 200 SMA and RSI
plot(sma200, color=color.blue, linewidth=2, title="200 SMA")
plot(rsi, color=color.purple, title="RSI", display=display.none)

// Define buy and sell conditions
var isLong = false
var float lastExitTime = na
var float trailStopPrice = na

// Explicitly declare timeSinceExit as float
float timeSinceExit = na(lastExitTime) ? na : (time - lastExitTime) / (24 * 60 * 60 * 1000)
canEnter = na(lastExitTime) or timeSinceExit > waitingPeriod

buyCondition = close > sma200 and rsi < rsiThreshold and canEnter

if (buyCondition and not isLong)
    strategy.entry("Buy", strategy.long)
    trailStopPrice := na
    isLong := true

// Update trailing stop loss if long
if (isLong)
    trailStopPrice := na(trailStopPrice) ? close * (1 - trailStopPercent / 100) : math.max(trailStopPrice, close * (1 - trailStopPercent / 100))

// Check for trailing stop loss or sell condition
if (isLong and (close < trailStopPrice or close < sma200))
    strategy.close("Buy")
    lastExitTime := time
    isLong := false

// Plot buy and sell signals
plotshape(series=buyCondition, title="Buy Signal", location=location.belowbar, color=color.green, style=shape.labelup, text="BUY")
plotshape(series=(isLong and close < trailStopPrice) or close < sma200, title="Sell Signal", location=location.abovebar, color=color.red, style=shape.labeldown, text="SELL")

Published by ChaoZhang on the FMZ strategy square · last modified 2025-01-17. Collected in the Quant Trading Vault. Unvalidated research: re-test with your own data and costs before trusting it.

Build this with AgenKit

A spec is not a trading system. Paste this into your coding agent and AgenKit runs a specialist team — architecture, test-first build, risk gates, review — with paper trading on by default.

in Claude Code, Cursor, Codex & 4 more

/agenkit build a production-grade trading bot with a backtest engine, risk controls and paper trading by default from strategies/Dynamic-Neural-RSI-Trend-Following-Trading-Strategy.md

npx agenkit install engineering-kit in your project
Paste the command into your agent and approve each phase
Get tests, backtest, risk controls and a paper-trading switch

Get AgenKit How /agenkit works

Understand it first

Before you run this, read the lesson behind the idea and how to backtest it honestly. Specs like this one are the survivors of an unknown number of trials; deflate their results accordingly.