πŸ”¬
Minerva AI (EN)
  • πŸ‘‹Welcome to Minerva AI
  • STUDIES & FINDINGS
    • ☝️Abstract
    • πŸ“Introduction and related works
    • πŸ’‘Model overview
      • ♾️Convolutional neural network - CNN
      • ✍️Dropout techniques
      • 🧠Long short-term memory (LSTM)
      • πŸ™†Methodology
      • πŸ”—Data collection and merging
      • πŸ› οΈModel architecture
      • βž•Dataset and Parameter Optimization
      • πŸ‘ŒResults and discussion
      • βš“Trading Philosophy & Method
      • βž—Basic algorithm
      • 🌠Results
    • πŸ‘‰Conclusion
  • PRODUCT DEVELOPMENT
    • πŸ‘€Vision and development roadmap
    • 🌟Revenue models
    • πŸͺ™Tokenomics
  • TEAM
    • πŸ‘₯Founding team
  • RESOURCES
    • πŸ“—References
Powered by GitBook
On this page
  1. STUDIES & FINDINGS
  2. Model overview

Basic algorithm

PreviousTrading Philosophy & MethodNextResults

Last updated 1 year ago

As mentioned earlier, this report introduces a novel approach to determine the movement of the cryptocurrency market. The model is optimized through different parameter settings as mentioned in Table 2. The model discussed in this report is designed to predict the closing price of Solana on the Spot Market (SOL/USDT). The algorithms used employ CNN architecture to predict the market direction with categorical target variables, while the model in this article has a continuous target variable. The models used in the reports by Hoseinzade E, Haratizadeh S (2019) and Kara Y, AcarBoyacioglu M, Baykan Γ–K (2011) were employed to evaluate the model. To address the issue of prediction variables, our model predictions are also transformed into categorical variables using the method discussed in the report by Hoseinzade E, Haratizadeh S (2019):

C(t): closing price of β€œth candle"

πŸ’‘
βž—