{"id":67,"date":"2022-01-19T12:53:00","date_gmt":"2022-01-19T12:53:00","guid":{"rendered":"https:\/\/eodhd.com\/financial-academy\/?p=67"},"modified":"2025-02-05T13:23:56","modified_gmt":"2025-02-05T13:23:56","slug":"what-happens-if-you-day-trade-crypto-with-facebook-prophet","status":"publish","type":"post","link":"https:\/\/eodhd.com\/financial-academy\/backtesting-strategies-examples\/what-happens-if-you-day-trade-crypto-with-facebook-prophet","title":{"rendered":"What Happens if you Day Trade Crypto with Facebook Prophet?"},"content":{"rendered":"\n

In the past, I\u2019ve experimented with various forms of machine learning models in order to develop a successful cryptocurrency trading strategy. These various strategies would utilize classification models<\/a>, time-series models<\/a>, and sentiment analysis<\/a>. The results of these strategies would range from mediocre to \u201cgood but requires more testing\u201d. I\u2019ve never settled on a specific strategy and hope to one day move on from the testing phase to \u201cactually implementing it with real money\u201d phase.<\/p>\n\n\n\n

In all of these different strategies, I have yet to change the frequency of the historical data tested. The frequency of data I have always used and backtested with was the daily historical price data<\/em>. That frequency for price data is not bad at all but it is limited, especially with the around the clock trading availability of the cryptocurrency market.<\/p>\n\n\n\n

So in order to continue my testing, I\u2019ll need to know what it is like to day trade crypto with machine learning. Specifically, I\u2019ll be using a time series machine learning model that I have found to be easy to use and implement \u2014 Facebook Prophet<\/em>. Feel free to code along with me or just continue reading to see the final outcome.<\/p>\n\n\n\n

Register & Get Data<\/span><\/a><\/p>\n\n\n\n

The Necessary Libraries and Data<\/h2>\n\n\n\n

To begin, I\u2019ll need to import some libraries:<\/p>\n\n\n\n

\n
\n \n
from eod import EodHistoricalData\nimport pandas as pd\nfrom datetime import datetime, timedelta\nimport calendar\nfrom tqdm import tqdm\nimport numpy as np\nimport random\nimport plotly.express as px\nfrom prophet import Prophet<\/code><\/pre>\n\n                <\/div>\n                
\n