Cryptocurrency Price Prediction Using Machine Learning

Parikh, Harsh; Panchal, Nisarg; Sharma, Ankit

doi:10.1007/978-981-19-2225-1_25

Cited by 2 publications

(2 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Dalam makalah ini, metode telah diusulkan untuk membangun model berbasis algoritma pembelajaran mesin seperti regresi linier, K-nearest neighbour (KNN), dan juga model statistik seperti Auto-ARIMA dan Facebook's Prophet (Fbprophet). Makalah ini menyajikan kinerja komparatif pembelajaran mesin dan algoritma pemodelan statistik untuk peramalan cryptocurrency [11].…”

Section: Pendahuluanunclassified

Prediksi Indeks Bursa Efek Indonesia 2023 Pendekatan ARIMA, Machine Learning dengan R Programming

Targa Sapanji,

Lestari,

Murnawan

et al. 2023

JAMIKA

View full text Add to dashboard Cite

The Indonesian Stock Exchange Index (BEI) is the main indicator of the Indonesian stock market. The problem in this research is a specific issue to solve the practical problem of predicting the future movement of the BEI index which has strategic value for investors, traders and companies in Indonesia. The aim of this research is to be able to predict the BEI index until the end of 2023, because the stock exchange plays a big role for the Indonesian economy as an economic and financial function. Traditional approaches such as ARIMA (Autoregressive Integrated Moving Average) have been used to predict the movement of the BEI index. However, in recent years, machine learning and data mining techniques have become popular as more sophisticated alternative approaches. This research uses a combined approach between ARIMA and machine learning with R Programming. Daily IDX index data from January 2012 to December 2022 will be taken from Yahoo Finance. This data will then be cleaned and processed using R Programming. The ARIMA approach will be used as a baseline to compare machine learning performance. The results focus on the estimated closing stock prices for the next 365 days or the average until the end of 2023. The Time Series value of the possible minimum/maximum predicted value for IDX shares in 2023 is a minimum predicted value of 6786,212 - 6849,559, a maximum predicted value of 6850,093 - 7086,012. Trends represent a good approach in predicting the future direction of closing prices.

show abstract

Section: Pendahuluanunclassified

Prediksi Indeks Bursa Efek Indonesia 2023 Pendekatan ARIMA, Machine Learning dengan R Programming

Targa Sapanji,

Lestari,

Murnawan

et al. 2023

JAMIKA

View full text Add to dashboard Cite

show abstract

“…Some studies, such as the one conducted by scientists at the Indian Institute of Technology, have shown the success of models such as linear regression, K-nearest neighbor (KNN), and statistical models such as Auto-ARIMA and Facebook's Prophet (Fbprophet) [8]. Individual scholars consider not only time series prediction tools but also complex multivariate portfolio analysis models [9].…”

Section: -Literature Reviewmentioning

confidence: 99%

Using PPO Models to Predict the Value of the BNB Cryptocurrency

Firsov¹,

Сильвестров²,

Kuznetsov³

et al. 2023

Emerg Sci J

View full text Add to dashboard Cite

This paper identifies hidden patterns between trading volumes and the market value of an asset. Based on open market data, we try to improve the existing corpus of research using new, innovative neural network training methods. Dividing into two independent models, we conducted a comparative analysis between two methods of training Proximal Policy Optimization (PPO) models. The primary difference between the two PPO models is the data. To showcase the drastic differences the PPO model makes in market conditions, one model uses historical data from Binance trading history as a data sample and the trading pair BNB/USDT as a predicted asset. Another model, apart from purely price fluctuations, also draws data on trading volume. That way, we can clearly illustrate what the difference can be if we add additional markers for model training. Using PPO models, the authors conduct a comparative analysis of prediction accuracy, taking the sequence of BNB token values and trading volumes on 15-minute candles as variables. The main research question of this paper is to identify an increase in the accuracy of the PPO model when adding additional variables. The primary research gap that we explore is whether PPO models specifically trained on highly volatile assets can be improved by adding additional markers that are closely linked. In our study, we identified the closest marker, which is a trading volume. The study results show that including additional parameters in the form of trading volume significantly reduces the model's accuracy. The scientific contribution of this research is that it shows in practice that the PPO model does not require additional parameters to form accurately predicting models within the framework of market forecasting. Doi: 10.28991/ESJ-2023-07-04-012 Full Text: PDF

show abstract

Cryptocurrency Price Prediction Using Machine Learning

Cited by 2 publications

References 10 publications

Prediksi Indeks Bursa Efek Indonesia 2023 Pendekatan ARIMA, Machine Learning dengan R Programming

Prediksi Indeks Bursa Efek Indonesia 2023 Pendekatan ARIMA, Machine Learning dengan R Programming

Using PPO Models to Predict the Value of the BNB Cryptocurrency

Contact Info

Product

Resources

About