Explore these ideas and more!
4 stars based on
We wanted to talk a little about the use case we picked for our book on machine learning pipelines. For the book, we decided to train a model that forecasts Bitcoin BTC prices and then use a big data streaming architecture to make trades based on our forecasts.
We use historical BTC price data available from Kaggle. This dataset contains years of minute-by-minute pricing. We then used a state of the art time series forecasting tool called Prophet which was recently open sourced by Facebook.
Prophet uses an additive regressive model to separate out the general price trend from hourly and daily cyclicality. This enables us to understand, minute by minute, what we expect to happen to price in the future—irrespective of the general trend in price.
In this way, the model could theoretically yield profitable trades without regard for whether price is going generally up or down. This provides us the entire stream of bid and ask orders placed on the Gemini exchange. We feed this to Kafka, a distributed streaming platform developed at LinkedIn. Kafka acts as glue for the analytic and trading components of the what language to i learn to write a trading bot pythonbusiness.
We then ingest this massive feed using Spark Streaming. We pass this analysis back to Kafka. Our trading bot takes the Spark processed data and, along with the forecasts we generated at the outset, executes trades. We use this example in our book to teach you how big data architectures work and how to build machine learning pipelines. Stay tuned for more updates on our progress! In this video, we talk about how we find the time to work on our upcoming book, Building Machine Learning Pipelines.
Be sure to use the form on the left to subscribe to our email list and get this video and more information about the book. Be sure to use the signup form on the left what language to i learn to write a trading bot pythonbusiness get all the behind-the-scenes action and announcements about the book!
One of the most important aspects of your book is its cover. The reason is that, when someone searches on Amazon or looks on a shelf, the cover is the first thing they see. You can get just about anything, and there are various price points. One of the cool things about 99D is its integration with Slack. Each time a design was posted on the site or a comment was made we got a notification:. Over the five days the contest ran we received a total of 34 designs from 14 designers.
Today we selected the winning design:. You may have heard the phrase above uttered by someone who wrote a book. It took more than three months while working a full-time job to complete the Python Business Intelligence Cookbook, and that book was mostly code!
Brandon and I were talking and thought it would be cool to bring you behind-the-scenes as we write our upcoming book — Building Machine Learning Pipelines. Be the first to get this behind-the-scenes view by filling out the signup form on the left side of this blog. Stream processing We then ingest this massive feed using Spark Streaming. Trading Our trading bot takes the Spark processed data and, along with the forecasts we generated at the outset, executes trades.
Each time a design was posted on the site or a comment was made we got a notification: As you can tell we got excited when we received our first entry within 1 hour! We highly recommend that if you use 99D you run a guaranteed what language to i learn to write a trading bot pythonbusiness. Today we selected the winning design: Writing a book is hard!
We look forward to sharing this experience with you!