Paper: arXiv 2503.18096
Authors: Filip Stefaniuk, Robert Ślepaczuk
Abstract
The article investigates the usage of Informer architecture for building automated trading strategies for high frequency Bitcoin data. Three strategies using Informer model with different loss functions: Root Mean Squared Error (RMSE), Generalized Mean Absolute Directional Loss (GMADL) and Quantile loss, are proposed and evaluated against the Buy and Hold benchmark and two benchmark strategies based on technical indicators. The evaluation is conducted using data of various frequencies: 5 minute, 15 minute, and 30 minute intervals, over the 6 different periods. Although the Informer-based model with Quantile loss did not outperform the benchmark, two other models achieved better results. The performance of the model using RMSE loss worsens when used with higher frequency data while the model that uses novel GMADL loss function is benefiting from higher frequency data and when trained on 5 minute interval it beat all the other strategies on most of the testing periods. The primary contribution of this study is the application and assessment of the RMSE, GMADL, and Quantile loss functions with the Informer model to forecast future returns, subsequently using these forecasts to develop automated trading strategies. The research provides evidence that employing an Informer model trained with the GMADL loss function can result in superior trading outcomes compared to the buy-and-hold approach.
Complexity vs Empirical Score
- Math Complexity: 6.5/10
- Empirical Rigor: 8.0/10
- Quadrant: Holy Grail — high math complexity, high empirical rigor
Why this score: The paper employs advanced machine learning architectures (Informer, Transformer-based) and novel loss functions (GMADL), representing moderate-to-high mathematical density. The empirical work is rigorous, utilizing high-frequency Bitcoin data across multiple timeframes and periods, with thorough backtesting against benchmarks, sensitivity analysis, and open-source implementation for reproducibility.
Research Flowchart
flowchart TD
A["Research Goal: Evaluate Informer architecture<br>for HFT Bitcoin trading strategies"] --> B["Data Processing"]
B --> C["Model Training & Forecasting"]
C --> D["Strategy Formulation"]
D --> E["Performance Evaluation"]
subgraph B ["Data & Inputs"]
B1["Bitcoin OHLCV Data"]
B2["High Frequency Intervals<br>5m, 15m, 30m"]
B3["Six Distinct Time Periods"]
end
subgraph C ["Computational Process"]
direction LR
C1["Informer Architecture"] --> C2{"Loss Functions"}
C2 --> C3["RMSE Loss"]
C2 --> C4["GMADL Loss"]
C2 --> C5["Quantile Loss"]
end
subgraph D ["Trading Logic"]
D1["Generate Return Forecasts"]
D2["Execute Buy/Sell Signals"]
D3["Benchmarks: Buy & Hold<br>Technical Indicators"]
end
subgraph E ["Key Outcomes"]
E1["RMSE: Performance degrades<br>with higher frequency data"]
E2["GMADL: Benefits from high frequency<br>Best overall performance"]
E3["Quantile: Underperformed<br>benchmarks"]
end
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 three Informer-based trading strategies using different loss functions (RMSE, GMADL, Quantile) for Bitcoin.
Source sentence
Three strategies using Informer model with different loss functions: Root Mean Squared Error (RMSE), Generalized Mean Absolute Directional Loss (GMADL) and Quantile loss, are proposed
Assumes 4
- Information Ratio is calculated assuming a risk‑free rate of zero. statistical
Source sentence
Information Ratio (IR*) The Sharpie ratio (Sharpe 1998) that is calculated under the assumption of a risk-free rate of zero.
- There are 365 days in a year for converting intervals to annual figures. data
Source sentence
It is assumed that there are 365 days in a year, so for the datasets used in the research, this value is equal to Y5m = 105120, Y15m = 35040 and Y30m = 17520.
- A flat transaction fee of 0.1% per trade is applied. execution
Source sentence
With transaction fee equal to 0.1% even if the asset price stays the same, already with log0.999(0.5) ≈692 incorrect position changes the portfolio value is halved
- The standard spot fee rate on Binance is used as the transaction cost. execution
Source sentence
The value is equal to standard spot fee rate on Binance https://www.binance.com/en/fee/trading
Data
BTC/USDT · crypto · intraday
- BTC/USDT price data market-prices public
Source sentence
The strategies were evaluated independently over six periods on BTC/USDT data of various frequencies: 5 minutes, 15 minutes, and 30 minutes.
Costs
Modeled
0.1% per trade (standard Binance spot fee).
Source sentence
... The value is equal to standard spot fee rate on Binance
Finds 4
annual return 115.9% · max drawdown 32.7%
- The GMADL Informer strategy trained on 5‑minute data achieved the highest performance, beating all other strategies and the buy‑and‑hold benchmark. performance
Source sentence
The best performing strategy was the one based on predictions of the Informer model trained on 5-minute data with the GMADL loss function.
- Eight strategies outperformed the buy‑and‑hold benchmark over the combined testing periods. performance
Source sentence
Hold benchmark, when compared throughout the testing period, i.e., combined results from all data windows.
- Higher‑frequency data improved the GMADL Informer strategy but deteriorated the RMSE Informer strategy. performance
Source sentence
usage of high frequency data improved the performance of the GMADL Informer strategy, while deteriorated the performance of the strategy based on the Informer with RMSE loss function.
- The GMADL Informer strategy achieved a VAL of 9.747, ARC of 115.88%, ASD of 54.44%, IR* of 2.129, and MD of 32.66% on 5‑minute data. performance
Source sentence
GMADL Informer 9.747 115.88% 54.44% 2.129 32.66% 7.552 846 44.80%
Checked by others
No other paper in the archive has been found to support or contradict these findings (compared with 27 related papers). Coverage is partial, so this is neither replication nor refutation.
3 papers in the archive
Extracted 2026-11-14 · same card as JSON · A language model chose these items: check the source sentence before relying on one.
Cited References (77)
- Generalized Mean Absolute Directional Loss as a Solution to Overfitting and High Transaction Costs in Machine Learning Models Used in High-Frequency Algorithmic Investment Strategies — → 2412.18405
- The efficiency of various types of input layers of LSTM model in investment strategies on S&P500 index (2022) — link
- Bitcoin: A Peer-to-Peer Electronic Cash System (2009)
- A Random Walk Down Wall Street (1973)
- Efficient Capital Markets: A Review of Theory and Empirical Work (1970)
- Efficient Capital Markets: II (1991) — link
- Reflections on the Efficient Market Hypothesis: 30 Years Later (2005) — link
- The Evolution of Technical Analysis: Financial Prediction from Babylonian Tablets to Bloomberg Terminals (2011) — link
and 69 more
- What Do We Know About The Profitability Of Technical Analysis? (2007) — link
- The Evolution Of Stock Market Efficiency Over Time: A Survey Of The Empirical Literature (2011) — link
- Stock return predictability and the adaptive markets hypothesis: Evidence from century-long U.S. data (2011) — link
- A Little Learning…: Confidence in Multicue Judgment Tasks (1978)
- Boys will be Boys: Gender, Overconfidence, and Common Stock Investment (2001) — link
- Learning To Be Overconfident (2001) — link
- Does the Stock Market Overreact? (1985)
- Prospect Theory: An Analysis of Decision under Risk (1979) — link
- Are Investors Reluctant to Realize Their Losses? (1996) — link
- Contagious Speculation and a Cure for Cancer: A Nonevent that Made Stock Prices Soar (2001) — link
- The Framing of Decisions and the Psychology of Choice (1981) — link
- Time Series Analysis: Forecasting and Control (1976)
- Stock price prediction using the ARIMA model (2014) — link
- A hybrid ARIMA and support vector machines model in stock price forecasting (2005) — link
- Time series forecasting using a hybrid ARIMA and neural network model (2003) — link
- Bitcoin Price Prediction: An ARIMA Approach (2018) — link
- Stock index forecasting based on a hybrid model (2012) — link
- Exponential smoothing model selection for forecasting (2006) — link
- A novel hybridization of artificial neural networks and ARIMA models for time series forecasting (2011) — link
- Long Short-Term Memory (1997) — link
- Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation (2014) — link
- Deep learning (2015) — link
- Forecasting Economics and Financial Time Series: ARIMA vs. LSTM. (2018) — link
- Application of machine learning in algorithmic investment strategies on global stock markets (2023) — link
- Artificial neural networks approach to the forecast of stock market price movements (2016)
- Recurrent Neural Networks Approach to the Financial Forecast of Google Assets (2017) — link
- Predicting Prices Of S&P 500 Index Using Classical Methods and Recurrent Neural Networks (2024) — link
- Hybrid Deep Learning Model for Stock Price Prediction (2018) — link
- Deep learning with long short-term memory networks for financial market predictions (2017) — link
- Stock price prediction using LSTM, RNN and CNN-sliding window model (2017) — link
- A LSTM-based method for stock returns prediction: A case study of China stock market (2015) — link
- Stock market’s price movement prediction with LSTM neural networks (2017) — link
- Gradient amplification: An efficient way to train deep neural networks (2020) — link
- Neural Machine Translation by Jointly Learning to Align and Translate (2014) — link
- Effective Approaches to Attention-based Neural Machine Translation (2015) — link
- Attention Is All You Need (2017) — link
- GPT-4 Technical Report (2024) — link
- Gemini: A Family of Highly Capable Multimodal Models (2024) — link
- Deep Learning for Time Series Forecasting : Tutorial and Literature Survey (2023) — link
- DeepAR: Probabilistic Forecasting with Autoregressive Recurrent Networks (2019) — link
- Temporal Fusion Transformers for Interpretable Multi-horizon Time Series Forecasting (2020) — link
- MQTransformer: Multi-Horizon Forecasts with Context Dependent and Feedback-Aware Attention (2020) — link
- Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting (2021) — link
- Exploring the Advantages of Transformers for High-Frequency Trading — → 2302.13850
- Attention! Transformer with Sentiment on Cryptocurrencies Price Prediction (2022) — link
- Stock Price Prediction Based on Temporal Fusion Transformer (2021) — link
- Beyond Sentiment in Stock Price Prediction: Integrating News Sentiment and Investor Attention with Temporal Fusion Transformer (2024) — link
- Cryptocurrency Price Prediction with LSTM and Transformer Models Leveraging Momentum and Volatility Technical Indicators (2023) — link
- A Stock Price Prediction Method Based on BiLSTM and Improved Transformer (2023) — link
- An Informer Based Method for Stock Intraday Price Prediction (2023) — link
- Advanced Stock Price Prediction Using LSTM and Informer Models (2024) — link
- Stock and market index prediction using Informer network — → 2305.14382
- BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding (2018) — link
- Daily and intraday application of various architectures of the LSTM model in algorithmic investment strategies on Bitcoin and the S&P 500 Index (2022) — link
- Momentum and contrarian effects on the cryptocurrency market (2019) — link
- Technical analysis: power tools for active investors (2005)
- New Concepts in Technical Trading Systems (1978) — link
- Xception: Deep Learning with Depthwise Separable Convolutions (2017) — link
- Gradient Flow in Recurrent Nets: The Difficulty of Learning LongTerm Dependencies (2001) — link
- Layer Normalization (2016) — link
- 1D Convolutional Neural Networks and Applications: A Survey (2019) — link
- Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs) (2016) — link
- Max-pooling convolutional neural networks for vision-based hand gesture recognition (2011) — link
- Deep Learning using Rectified Linear Units (ReLU) (2019) — link
- Mean Absolute Directional Loss as a new loss function for machine learning problems in algorithmic investment strategies — → 2309.10546
- How algorithmic trading undermines efficiency in capital markets (2015)
- Markov processes over denumerable products of spaces, describing large systems of automata (1969)
- Bollinger on Bollinger Bands (2002) — link
- Applying Hybrid ARIMA-SGARCH in Algorithmic Investment Strategies on S&P500 Index (2022) — link
4 of 77 cited works are in the corpus; resolved via arXiv source bundles, Semantic Scholar and OpenAlex. Corpus-wide: 2596 linked papers.