Paper: arXiv 2405.14262
Authors: Abdul Rahman
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.
Complexity vs Empirical Score
- Math Complexity: 5.5/10
- Empirical Rigor: 6.0/10 (capped from 6.5: transaction costs not modelled; see penalty flags)
- Quadrant: Holy Grail — high math complexity, high empirical rigor (effective empirical rigor capped from 6.5)
Why this score: The paper applies Bayesian optimization, which involves probabilistic modeling and Gaussian processes (advanced math), while also evaluating the optimized strategy via backtesting on multiple stock datasets with performance metrics like profit factor and maximum drawdown, indicating significant empirical implementation.
Research Flowchart
flowchart TD
A["Research Goal:<br>Optimize Supertrend Parameters<br>via Bayesian Optimization"] --> B["Input: Diverse Stock Datasets"]
B --> C["Method: Bayesian Optimization<br>Search Space: ATR Multiplier & Period"]
C --> D["Process: Backtesting<br>Evaluated for Trading Profits"]
D --> E{"Comparison: BO-Optimized vs<br>Manual Parameters"}
E -->|"Outcome"| F["Key Finding:<br>Data-Driven Strategy with<br>Maximized Returns"]
E -->|"Outcome"| G["Key Finding:<br>Automated Parameter Identification"]
Evidence Card
What the authors claim, on what data, and who has checked it. Read from the paper's own text by a language model: every quote is verbatim, nothing was re-run. How to read this card
Proposes
The paper proposes using Bayesian optimization to automatically find optimal atr multiplier and period settings for the Supertrend indicator to maximize trading profits.
Source sentence
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.
Assumes
No explicit assumptions found in the text.
Data
multiple stocks (Nifty 50, Infosys, Hindustan Unilever, Micr · equities · daily
- Five stock datasets market-prices unknown
Source sentence
applying the Supertrend strategy with default atr multiplier (3) and atr period (15) to the collected datasets for the five stocks: Nifty 50, Infosys, Hindustan Unilever, Microsoft, and Nvidia.
Yahoo Finance
Costs
Not modeled
Finds 1
max drawdown 6.6%
- Optimised parameters yield higher profits than the default Supertrend settings within a limited number of BO iterations. performance
Source sentence
Observation: Optimised Parameters perform better than default supertrend parameters under a constrained number of iterations.
Checked by others
No other paper in the archive has been found to support or contradict these findings (compared with 16 related papers). Coverage is partial, so this is neither replication nor refutation.
Extracted 2026-11-14 · same card as JSON · A language model chose these items: check the source sentence before relying on one.
Cited References (14)
- Real-time segmentation of on-line handwritten arabic script (2014)
- A Study of Key Technical Indicators for Effective and Profitable Strategy in Option Trading of Nifty (2022)
- Fast classification of handwritten on-line Arabic characters (2014) — link
- A Study of Key Technical Indicators for Effective and Profitable Strategy in Option Trading of Nifty (2022)
- Performance Analysis of Supertrend Trading Strategy on Indian Stock Market (2017)
- A Comparative Study of Supertrend and Moving Average Crossover Trading Strategies (2016)
- Optimizing Trading Strategies with Bayesian Optimization (2020)
- Bayesian Optimization for Algorithmic Trading (2016)
and 6 more
- Taking the Human Out of the Loop: A Review of Bayesian Optimization (2016) — link
- New technique for stock trend analysis-volume-weighted squared moving average convergence and divergence (2023) — link
- Balanced baskets: A new approach to trading and hedging risks (2012) — link
- Deep reinforcement learning pairs trading with a double deep Q-network (2020) — link
- Ensembling and dynamic asset selection for risk-controlled statistical arbitrage (2021) — link
- Stock price prediction using time series, econometric, machine learning, and deep learning models (2021)
0 of 14 cited works are in the corpus; resolved via arXiv source bundles, Semantic Scholar and OpenAlex. Corpus-wide: 2596 linked papers.