Bitcoin Price Prediction: Pros & Cons of Various Methods Used for Predicting Bitcoin Prices

A lot of research has been carried out on Bitcoin price prediction and the results have been used for predicting Bitcoin prices. Whenever researchers are interested in predicting the price of Bitcoin in their research, they try their best to consider all the various parameters that affect Bitcoin price or value.

When assessing various research papers on Bitcoin price prediction and the respective methodologies employed in predicting prices of Bitcoin in each research, one would easily notice that even though many research works accurately predicted Bitcoin prices, some others didn’t.

From the papers on some research works that didn’t accurately predict Bitcoin prices, it can be noticed and argued that higher time complexities are associated with inaccurate predictions; i.e., the algorithms that were used in the research works didn’t manage time to a great extent. Time complexity can be reduced—or time management can be enhanced to a great extent—by using the “Least Absolute Shrinkage Selection Operator” algorithm, also known as the LASSO algorithm.

LASSO isn’t discussed in this article, but if you’re interested in reading about an algorithm that is linked to artificial intelligence and was used to accurately predict Bitcoin prices in a particular research work, you can do so by clicking here (Bitcoin Price Prediction Using Machine Learning Algorithms, by Lekkala Sreekanth Reddy & Dr.P. Sriramya). After conducting out the research, the researchers concluded that the LASSO algorithm would be able to help customers make profits and increments.

The Advantages & Disadvantages of Methodologies Applied in Researches on Bitcoin Price Prediction

1. Title of Research Paper: Predicting Bitcoin Prices Using Deep Learning

Algorithm Applied: SVM (Support Vector Machine)

Advantages (Pros):

  • It is much more convincing to use it in high-dimensional spaces like those occupied by random vectors.
  • It works well in cases that have a clear margin of separation.
  • It is effective in cases where the number of samples is lesser than the number of dimensions.

Disadvantages (Cons):

  • It doesn’t perform to a great extent or high degree when applied to a large set of data.
  • Its performance level is low when it is applied to a noisy set of data.

2. Title of Research Paper: Bitcoin Price Prediction using Machine Learning

Algorithms Applied: Bayesian Regression and GLM/Random Forest

Advantages (Pros):

  • It makes a prediction based on information readily available on the coinMarkup cap.
  • It can easily make use of Quandl to filter any set of data by employing MAT lab properties.

Disadvantages (Cons):

  • It takes a long period of time to filter any set of data.
  • It has a low redundancy to perform a prediction.

3. Title of Research Paper: Bitcoin Volatility Forecasting with a Glimpse into Buy and Sell Orders

Algorithms Applied: LSTM (Long Short Term Memory) and ARIMA (Autoregressive Integrated Moving Average)

Advantages (Pros):

  • It makes it easy to buy and sell Bitcoins.
  • It enables transactions to be carried out comfortably.

Disadvantages (Cons):

  • It doesn’t give proof for a transaction.
  • Conversions are late.

4. Title of Research Paper: Bayesian regression and Bitcoin

Algorithm Applied: Bayesian Regression

Advantages (Pros):

  • The results of Bitcoin price prediction can be presented in terms of binary values.
  • It makes Bitcoin price prediction results to be clearly understood.

Disadvantage (Con):

  • It takes a long time for a set of data to be solved.

5. Title of Research Paper: Project-Based Learning: Predicting Bitcoin Prices using Deep Learning

Algorithms Applied: CNN (Convolutional Neural Networks) and RNN (Recurrent Neural Networks)

Advantages (Pros):

  • It provides weight sharing (through CNN) which significantly reduces the number of weights that have to be learned.
  • It enables large data set prices to be easily calculated.

Disadvantage (Con):

  • With the Convolutional Neural Networks algorithm involved, operations are significantly slower in both forward and backward directions.


Farokhmanesh F., & Sadeghi M. T. (2019). “Deep Feature Selection using an Enhanced Sparse Group Lasso Algorithm”. 2019, 27th Iranian Conference on Electrical Engineering (ICEE).

Huisu Jang, & Jaewook Lee, “An Empirical Study on Modelling and Prediction of Bitcoin Prices with Bayesian Neural Networks based on Blockchain Information”, in IEEE Early Access Articles, 2017, vol. 99, pp. 1–1.

Kalpanasonika, Sayasri S., Vinothini, & Suga Priya, “Bitcoin Cost Prediction using Deep Neural Network Technique”, IEEE 2018.

S. Yogeshwaran, Piyush Maheshwari & Maninder Jeet Kaur, “Project-Based Learning: Predicting Bitcoin Prices using Deep Learning”, Amity University Dubai Dubai, UAE; IEEE 2019.

Siddhi Velankar, Sakshi Valecha & Shreya Maji, “Bitcoin Price Prediction using Machine Learning”, Department of Electronics & Telecommunication, Pune Institute of Computer Technology, Pune, Maharashtra, India: 409–415.

Tian Guo, Albert Bifet, & Nino Antulov-Fantulin, “Bitcoin Volatility Forecasting with a Glimpse into Buy and Sell Orders”; IEEE 2018.

Leave a Reply

Fill in your details below or click an icon to log in: Logo

You are commenting using your account. Log Out /  Change )

Google photo

You are commenting using your Google account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s

This site uses Akismet to reduce spam. Learn how your comment data is processed.