
How To Build Stock Price Prediction Without Writing a Single Line of Code
How To Build Stock Price Prediction Without Writing a Single Line of Code. In this post you will learn how to use Amazon SageMaker Canvas to generate predictions without writing code.
- Part 1 - Configuring prerequisites and obtaining a dataset
- Part 2 - Building predictions with SageMaker Canvas
- Part 3 - Using the model to generate predictions
- Part 4 - Creating a visualization dashboard using QuickSight
- Obtain a historical dataset from Nasdaq
- Modify the dataset and upload it to Amazon S3 bucket
- Use SageMaker Canvas to build a model
- Visualize the forecasted dataset using Amazon QuickSight
Predictions
. We will need to create a new IAM role to allow access to your AWS account. Click Create a new role, then select Any S3 bucket and click Create New Role. Once it’s done, click Submit at the bottom of the page.- Add a Column Ticker with value AAPL
- Rename Close/Last to MarketClose
- Rename Open to MarketOpen
- Set Format Cells to Number with 2 decimals for the following fields: MarketClose, MarketOpen, High, Low.
AAPL Predictions
- and click the Create button.On the next screen, select your dataset and click the Select dataset button at the bottom.
- Quick build – Builds a model in a fraction of the time compared to a standard build. It results in potentially lower accuracy in exchange of greater speed. It takes about 15-20 minutes to complete Quick Build.
- Standard build – Builds the best model from an optimized process powered by AutoML. It takes a longer time but provides more accurate results. It may take around 4-5 hours to build a model using our dataset.
Quick note:Amazon SageMaker Canvas's 2-month free tier includes workspace instance (Session-Hrs) usage up to 750 hours/month for using the SageMaker Canvas application.
- The column that uniquely identifies items in the dataset: Ticker
- The column that contains the time stamps: Date
- Specify Number of days for forecast: 30
- Use holiday schedule: Enable and pick United States. The Nasdaq Stock Market is closed during the US holidays.
- Aggregation: No aggregation
- Filter condition: Greater than
- Minimum value: 1
Any opinions in this post are those of the individual author and may not reflect the opinions of AWS.