Available translations

Data Mining - Workflows

foundations.png
Summary: Superalgos enables users to setup powerful data mining operations. This page will introduce the workflows that are involved in data mining.
In general, data flows from the Internet into the Superalgos system. Once inside, it is then processed and reprocessed and finally consumed by trading strategies.
Two Main Data Workflows
  • Sensor Bot Workflow: Data arrives into the system through a Sensor Bot. In this main workflow, the resulting dataset serves as an input for an Indicator Bot that will further process it.
Raw Data -> Indicator Bots
Indicator bots have two different purposes:
  • Standardize Datasets: They are used for standardization of raw data extracted from the Internet by a Sensor Bot or an API Data Fetcher Bot. Once data is standardized, it can be run through other Indicator Bots that will extract the juice out of them. Once standardized, data can also be plotted and consumed by Trading Strategies. By standardizing, we are specifically referring to transforming the data into a Dataset type that can be used for plotting charts, or feeding Learning and Trading Bots. These Dataset types are Multi-Time-Frame-Daily and Multi-Time-Frame-Market.
  • Process Data: This means processing the data in any way that makes sense for users. Many users use Indicator Bots to calculate standard indicators, others calculate non-standard stuff, even ideas of what could be useful to extract from a certain dataset can be implemented. The system is open and allows users to do just that, play with the data by transforming it in any way they wish.
Indicators -> Plotters
Plotters are tools for users, not for bots. Plotters will render the information of a Dataset at the charts based on the plotter's definition. This allows users to visually discover patterns in datasets and generate ideas. These ideas can then help the user decide how to process the data further or feed the data to a Learning Bot or a Trading Bot.
Indicators -> Learning Bots (under development)
Learning Bots have access to mined data which they use to train their AI Models. Once trained, these AI Models can be used by trading strategies to request predictions and act upon them.
Indicators -> Trading Bots
Trading bots are the ultimate consumer of data. They use the data they receive to make trading decisions based on their definitions. The ultimate purpose of the whole Data Mining operation is to digest data so that it is easily accessible for trading strategies.
Previous
Data Mining - Introduction
Next
Data Mining - Dataset Types

Data Mining — TOC

You just read page 2 in the topic.

1. Data Mining - Introduction

2. Data Mining - Workflows

3. Data Mining - Dataset Types

4. Data Mining - Datasets Type Conversions

5. Data Mining - Indicator Frameworks

6. Data Mining - Data Mine Hierarchy

7. Data Mining - Managing Execution

8. Data Mining - Data Dependencies

9. Data Mining - Status Reports

10. Data Mining - Status Dependencies

11. Data Mining - Deployments

12. Data Mining - Products

13. Data Mining - Plotting

14. Data Mining - Fetching Data From APIs

15. Data Mining - Consuming Data From Strategies

16. Data Mining - Indicator Bots

17. Data Mining - Indicator Bots - Process Definition

18. Data Mining - Indicator Bots - Product Definition

19. Data Mining - Indicator Bots - Data Mining Workflow

20. Data Mining - Indicator Bots - Coding the Indicator's Logic

21. Data Mining - Plotters

22. Data Mining - Plotters - Shapes

23. Data Mining - How to Build an Indicator - Video Series