Unlocking Profit Potential: Maximizing Returns with Bayesian Optimization of Supertrend Indicator Parameters

TL;DR

This paper explores using Bayesian optimization to automatically tune Supertrend indicator parameters, aiming to enhance trading profitability across various stock datasets through data-driven parameter selection.

Contribution

It introduces a Bayesian optimization approach for tuning Supertrend parameters, providing a systematic method to improve trading strategies over manual tuning.

Findings

BO-optimized parameters outperform manual settings in backtests

Enhanced profitability demonstrated across multiple stock datasets

Automated parameter tuning reduces manual effort and bias

Abstract

This paper investigates the potential of Bayesian optimization (BO) to optimize the atr multiplier and atr period -the parameters of the Supertrend indicator for maximizing trading profits across diverse stock datasets. By employing BO, the thesis aims to automate the identification of optimal parameter settings, leading to a more data-driven and potentially more profitable trading strategy compared to relying on manually chosen parameters. The effectiveness of the BO-optimized Supertrend strategy will be evaluated through backtesting on a variety of stock datasets.