Paper: arXiv 2403.03410

Authors: Novan Fauzi Al Giffary, Feri Sulianta

Abstract

The rapid development of information technology, especially the Internet, has facilitated users with a quick and easy way to seek information. With these convenience offered by internet services, many individuals who initially invested in gold and precious metals are now shifting into digital investments in form of cryptocurrencies. However, investments in crypto coins are filled with uncertainties and fluctuation in daily basis. This risk posed as significant challenges for coin investors that could result in substantial investment losses. The uncertainty of the value of these crypto coins is a critical issue in the field of coin investment. Forecasting, is one of the methods used to predict the future value of these crypto coins. By utilizing the models of Long Short Term Memory, Support Vector Machine, and Polynomial Regression algorithm for forecasting, a performance comparison is conducted to determine which algorithm model is most suitable for predicting crypto currency prices. The mean square error is employed as a benchmark for the comparison. By applying those three constructed algorithm models, the Support Vector Machine uses a linear kernel to produce the smallest mean square error compared to the Long Short Term Memory and Polynomial Regression algorithm models, with a mean square error value of 0.02. Keywords: Cryptocurrency, Forecasting, Long Short Term Memory, Mean Square Error, Polynomial Regression, Support Vector Machine

Complexity vs Empirical Score

  • Math Complexity: 4.0/10
  • Empirical Rigor: 6.0/10
  • Quadrant: Street Traders — empirical and applied, lower math complexity

Why this score: The paper uses standard machine learning models (LSTM, SVM, Polynomial Regression) with established equations, but lacks deep mathematical derivation or novel theory, while the empirical work involves real data, data splitting, and comparison metrics like MSE.

Research Flowchart

  flowchart TD
  A["Research Goal: Predict Cryptocurrency Prices"] --> B["Data: Historical Crypto Prices"]
  B --> C["Methodology: Three Algorithms"]
  C --> D["LSTM<br>Long Short-Term Memory"]
  C --> E["SVM<br>Support Vector Machine"]
  C --> F["PR<br>Polynomial Regression"]
  D --> G["MSE Calculation"]
  E --> G
  F --> G
  G --> H{"Performance Comparison"}
  H --> I["Key Finding: SVM produced lowest MSE 0.02"]

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 to compare Long Short Term Memory, Support Vector Machine, and Polynomial Regression models for cryptocurrency price forecasting to identify the most suitable algorithm.

Source sentence
By utilizing the models of Long Short Term Memory, Support Vector Machine, and Polynomial Regression algorithm for forecasting, a performance comparison is conducted to determine which algorithm model is most suitable for predicting crypto currency prices.

Assumes 5

  • Mean Square Error is used as the benchmark metric for model performance. statistical
    Source sentence
    Mean Square Error (MSE) served as the benchmark, revealing that the LSTM method exhibited lower MSE compared to linear regression.
  • The dataset is split into 80% training and 20% testing. data
    Source sentence
    After normalization, the data allocated into two categories: training data and testing data, with an 80:20 ratio for training and testing, respectively.
  • Data are normalized and null values are removed to minimize errors during testing. data
    Source sentence
    the dataset undergoes normalization to eliminate null values, minimizing errors during algorithm model testing.
  • The Support Vector Machine uses a linear kernel. model
    Source sentence
    the Support Vector Machine uses a linear kernel to produce the smallest mean square error compared to the Long Short Term Memory and Polynomial Regression algorithm models
Show 1 more
  • Training of the LSTM model is performed with multiple epoch settings (10, 30, 50, 80, 100). model
    Source sentence
    the training process is iterated multiple times with varying Epoch numbers specifically, 10, 30, 50, 80, and 100, to achieve the best accuracy results.

Data

  • Bitcoin price data · Yahoo Finance market-prices public
    2020-2024 · Bitcoin
    Source sentence
    the research data comprises Bitcoin price data from 2020 to 2024 obtained from the Yahoo Finance website.

Recognised sources: Yahoo Finance

Costs

Not applicable The paper reports no trading or execution result.

Finds 2

  • The Support Vector Machine model achieved the lowest mean square error of 0.02 among the three algorithms. predictive-accuracy
    Source sentence
    Among all three Algorithm models tested, the Support Vector Machine algorithm model shows the lowest mean square error value at 0.02.
  • The Polynomial Regression model produced the highest mean square error of 51702001.51. predictive-accuracy
    Source sentence
    the Polynomial Regression algorithm model produced the highest mean square error amount at 51702001.51.

Checked by others

No other paper in the archive has been found to support or contradict these findings (compared with 11 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.