Paper: arXiv 2311.06280

Authors: Parth Daxesh Modi, Kamyar Arshi, Pertami J. Kunz, Abdelhak M. Zoubir

Abstract

Bitcoin as a cryptocurrency has been one of the most important digital coins and the first decentralized digital currency. Deep neural networks, on the other hand, has shown promising results recently; however, we require huge amount of high-quality data to leverage their power. There are some techniques such as augmentation that can help us with increasing the dataset size, but we cannot exploit them on historical bitcoin data. As a result, we propose a shallow Bidirectional-LSTM (Bi-LSTM) model, fed with feature engineered data using our proposed method to forecast bitcoin closing prices in a daily time frame. We compare the performance with that of other forecasting methods, and show that with the help of the proposed feature engineering method, a shallow deep neural network outperforms other popular price forecasting models.

Complexity vs Empirical Score

  • Math Complexity: 3.5/10
  • Empirical Rigor: 4.0/10
  • Quadrant: Philosophers — conceptual discussion, lower math and empirical scores

Why this score: The paper employs standard deep learning architectures (Bi-LSTM) and statistical metrics (MAE, RMSE, MAPE) without advanced mathematical derivations, while the empirical approach relies on a limited, single-asset dataset with a custom train-test splitting strategy rather than rigorous backtesting across multiple assets or market regimes.

Research Flowchart

  flowchart TD
  A["Research Goal: Daily Bitcoin Closing Price Forecast"] --> B["Data Source: Historical Bitcoin Time-Series Data"]
  B --> C{"Proposed Methodology"}
  C --> D["Proposed Feature Engineering"]
  C --> E["Baseline Methods Comparison"]
  D --> F["Model Architecture: Shallow Bi-LSTM"]
  E --> G["ARIMA, LSTM, etc."]
  F --> H["Evaluation: RMSE, MAE"]
  G --> H
  H --> I["Outcome: Proposed FE + Shallow Bi-LSTM Outperforms Baselines"]

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 a shallow Bidirectional‑LSTM model combined with a novel feature‑engineering method to forecast daily Bitcoin closing prices.

Source sentence
As a result, we propose a shallow Bidirectional-LSTM (Bi-LSTM) model, fed with feature engineered data using our proposed method to forecast bitcoin closing prices in a daily time frame.

Assumes 5

  • Deep learning models require a vast amount of data, which is limited for Bitcoin price prediction. data
    Source sentence
    Since deep learning models require a vast amount of data, one of the main challenges in bitcoin price prediction is that the available data is limited
  • Data augmentation techniques cannot be applied to historical Bitcoin data. data
    Source sentence
    There are some techniques such as augmentation that can help us with increasing the dataset size, but we cannot exploit them on historical bitcoin data.
  • The target is to predict the next day’s closing price using daily OCHL data. model
    Source sentence
    We aim to predict the closing price of the next day using this dataset.
  • Raw transaction features are highly correlated, which may cause over‑fitting. statistical
    Source sentence
    ... Using raw transactions may lead to overfitting of the machine learning (ML) models
Show 1 more
  • A shallow network reduces computational complexity while maintaining performance. model
    Source sentence
    feed our features into a shallow Bi‑LSTM network to not only decrease computational complexity but also having a promising performance.

Data

  • Bitcoin daily OCHL prices · InvestPy API market-prices public
    January 2013 until September 2021 · Bitcoin
    Source sentence
    We used the bitcoin’s OCHL prices for each day from January 2013 until September 2021 while extracting and selecting some of the most important indicators for our task as our dataset for training and validation.
  • Bitinfocharts on‑chain features · Bitinfocharts crypto-onchain public
    Bitcoin
    Source sentence
    Other than collecting OCHL daily bitcoin transaction prices (4 features), we utilized Bitinfocharts1 to extract 19 raw features: transactions in blockchain, average block size, sent by address, average mining difficulty, average hashrate, mining profitability, sent coins in USD, average transaction fees, median transac

Costs

Not applicable The paper reports no trading or execution result.

Finds 1

  • The proposed Bi‑LSTM model consistently outperforms other forecasting methods in terms of RMSE, MAE, and MAPE on both training and test sets. performance
    Source sentence
    We can observe in Table I that our proposed Bi-LSTM is performing more consistently and better comp…

Checked by others

No other paper in the archive has been found to support or contradict these findings (compared with 18 related papers). Coverage is partial, so this is neither replication nor refutation.

Code

No repository by the authors found in the paper.

Extracted 2026-11-14 · same card as JSON · A language model chose these items: check the source sentence before relying on one.