Tuomas Poukkula - Published 13.7.2020 - updated 4.11.2020

  1. 2020-07-13-060334.263854vaestometsa-1.PNG
  2. 2020-07-13-060334.298916vaestometsa-2.PNG

With the VäestöMetsä (PopulationForest) application you can test how well the Random Forest technology can predict the development of population in Finland. Random Forest is a type of ensemble machine learning method that can be used to gain a higher quality prediction by combining multiple learning methods. In this case, the Random Forest consists of decision trees that all try to create a prediction. The final prediction is the average of all the decision trees' results. An important factor when using a Random Forest is the amount of trees. In this application, you can select the amount of trees yourself. You can also adjust other factors affecting the end results, such as the municipality and the length of the prediction.

The VäestöMetsä application was created as a tool to learn more about machine learning. We hope you have fun with creating predictions and learning about predictive analytics with the help of this app.

VäestöMetsä application only works in Finnish.

Used datasets