Andrew Carr Elastic Engineer
Agriculture
PlaceHolder: Map
DevOps
Calculus: 3Blue1Brown
Financial markets and software engineering: Part Time Larry (YouTube)
Overall Approach
FastAI Model
50.3% Accuracy
# Python
import pandas as pd
from prophet import Prophet
df = pd.read_csv('https://raw.githubusercontent.com/facebook/prophet/main/examples/example_wp_log_peyton_manning.csv')
m = Prophet()
m.fit(df)
future = m.make_future_dataframe(periods=365)
future.tail()
forecast = m.predict(future)
fig1 = m.plot(forecast)
Trading bot currently running on AWS EC2 within Docker image
Problems with current approach
Cannot beat market with limited data. Copy others?
Time to change market!
More Data and better Trained!
Utilisation of FastAI's tsai library
Modelling of Commodities