Due to recent updates, all users are required to create an Altair One account to login to the RapidMiner community. Click the Register button to create your account using the same email that you have previously used to login to the RapidMiner community. This will ensure that any previously created content will be synced to your Altair One account. Once you login, you will be asked to provide a username that identifies you to other Community users. Email us at Community with questions.
"Machine Learning with the Neural Network"
florianklimek
Member Posts: 3 Contributor I
Hey guys,
I'm a student and have a particular question for a project at university. We have data about all countries in the world regarding the broadband penetration and the Human Development Index in the years 2000, 2005 and 2010 - 2014.
Now we would like to make a prediction about how the broadband penetration could affect the HDI in the future using the neural network or another method you would recommend. In the end, we would like to see that if for example Brazil risens the broadband penetration by 1% the HDI will rise by the number x.
Can you help us how to manage that?
Thank you and kind regards!
Tagged:
0
Answers
Hi @florianklimek,
I don't know if your project is a regression problem or a time serie problem.
In the first case, you can use the Linear Regression or Vector Linear Regression operators (HDI vs broadband penetration).
but can you share your dataset(s) to better understand ?
Regards,
Lionel
Thank you for your reply!
Of course, here is the data. Ignore the other data, first of all we are focused on Broadband and the overall HDI.
Thanks!
Hi @florianklimek
You have little data, however they are well fitted by a Linear Regression model (R2 micro = 0,977) :
hyhhy
1. you can set the country to study by sethis country in the Set country operator
2. I performed this study with Human Development Index (HDI), if you want to study the HDI set HDI in the Select Attribute and Set role operators.
3. You can set your future Broadband by setting them in the Future Broadband operator to predict your future HDI.
Here the process :
I hope it will be helpful,
Regards,
Lionel
Thank you very much, Lionel!
Really a great community here! But we have two more questions. So the process calculates all the numbers from each year right? So how can we interpretate the results?
Thanks a lot!
Hi @florianklimek,
The process fit your data with Linear Regression Model.
In your case, the equation of the model is :
Human Developement Index (HDI) = 0,006 * BroadBand Penetration + 0.685
So you can use this equation to predict the Human Developement Index (HDI) for a given BroadBand Penetration.
NB : Connect one of the Multiplier(2) output (which is a model output) to the result (res) to see the parameters of the regression model.
I hope it will be helpful,
Regards,
Lionel