CryptoForecasting using Machine and Deep learning (Part 1)

CryptoForecasting using Machine Learning

The main aspect of predicting the stock-related data is its variance with time. We can project the possible price of the dataset when it reaches a specific time.

Part - I Forecasting prices using Facebook/Meta's Prophet model

Developed by Facebook's Core Data Science Team, FBProphet is widely used in machine learning for forecasting time series for instances that involve time series data with all kinds of seasonalities (yearly, weekly and monthly) including holidays and vacations. This is part one of the series on CryptoForecasting using Machine Learning. I have used Facebook's Prophet model to predict the model for the same.

Prophet is also suitable for historical data with several seasons. To carry out the process of regression, FBProphet uses time as a regression variable (regressor) along with the time series' linear and non-linear parameters as components. The data can be fitted into the model which can be changed from linear (default) to non-linear in FBProphet as per the requirements.

Forecasting prices using Facebook/Meta's Prophet model

Related tags

Overview

CryptoForecasting using Machine and Deep learning (Part 1)

Owner

TensorFlow Decision Forests (TF-DF) is a collection of state-of-the-art algorithms for the training, serving and interpretation of Decision Forest models.

A library to generate synthetic time series data by easy-to-use factors and generator

A series of Jupyter notebooks that walk you through the fundamentals of Machine Learning and Deep Learning in Python using Scikit-Learn, Keras and TensorFlow 2.

Dragonfly is an open source python library for scalable Bayesian optimisation.

Responsible Machine Learning with Python

Tutorials, examples, collections, and everything else that falls into the categories: pattern classification, machine learning, and data mining

Management of exclusive GPU access for distributed machine learning workloads

Petastorm library enables single machine or distributed training and evaluation of deep learning models from datasets in Apache Parquet format. It supports ML frameworks such as Tensorflow, Pytorch, and PySpark and can be used from pure Python code.

customer churn prediction prevention in telecom industry using machine learning and survival analysis

An MLOps framework to package, deploy, monitor and manage thousands of production machine learning models

Distributed Evolutionary Algorithms in Python

dirty_cat is a Python module for machine-learning on dirty categorical variables.

DaCeML - Machine learning powered by data-centric parallel programming.

Kaggler is a Python package for lightweight online machine learning algorithms and utility functions for ETL and data analysis.

Python Automated Machine Learning library for tabular data.

Hypernets: A General Automated Machine Learning framework to simplify the development of End-to-end AutoML toolkits in specific domains.

The Simpsons and Machine Learning: What makes an Episode Great?

Scikit-Learn useful pre-defined Pipelines Hub

Data Efficient Decision Making

My capstone project for Udacity's Machine Learning Nanodegree