A model for prices référence

Nshims

New Member
Joined
May 28, 2014
Messages
227
Points
18
As I mentioned in the following post https://forum.pokemo... I took a moment to create a neural network perceptron capable of predicting prices for pokémons, based on ivs and whether or not the pokemon is S. Basically it works like a normal multilayer perceptron, the trick is simply how the information is preprocessed and post processed.

At first I told myself that pokemons of a certain category can not exceed a certain price. Immediately we can imagine that there is a lower margin and an upper margin, in this case taking the upper margin as the limit of all possible prices and 0 as the lower margin. As the set of prices is limited and closed theoretically we can say that there is a given price for each pokémon belonging to the category, this amounts to looking for a bijection between all the ivs and all the prices.

But in practice we tend to give rounded prices, almost no one gives a price such as 153,024 Pd for example, so we can speak of injection for the practical part or even non-function in some extreme cases.

Basically what the algorithm will do is to look for a series of linear combinations that could give the answer as close as possible to the expected result.

Here the pokémons that I used for the tests.
img.png

The first 10 pokémons serve as training data and the last 3 serves as testing data. Before you ask why there is a pokemon labeled in the test column, let me tell you that all the pokemons are tagged, it's just a different way of doing it.
Also after several trainings I noticed that one of them posed a problem because its price was badly chosen, so I decided to put it in the training data set, it will the act like a anti overfitting since I have not yet set up a system to counter this.

For the rest it was necessary to train several individuals and see what comes out to deduct the best prices for test pokémon.
t1.png

One thing that stands out is the fact that in the training data the prices are perfectly predicted, which may be a sign of overfitting if we have not put in place a system to counter it, but for the moment it does not cause problems.
We can also see that in the test data the predicted prices are very close to the original prices, taking into account the margin of error for a given set of test data, It is possible to give a range of possible prices for a given pokemon.

Here some other examples trained on the same data.
t2.png
t3.png
t4.png

The results are not bad but can be improved by increasing the amount of correctly labeled training data, also increasing the amount of test data can improve the verification of the quality of the results.
It is a simple example to try to solve a given problem, but the algorithms can be improved and combined to solve more complex problems.

Let me know what you think about. :)
 

Kingstone

New Member
Joined
Aug 3, 2015
Messages
90
Points
18
Great job, I find this idea very interesting, particularly I like it a lot, it will be a lot of work, but it can help a huge number of players, count on my help, in case you need something.
 

Nshims

New Member
Joined
May 28, 2014
Messages
227
Points
18
Great job, I find this idea very interesting, particularly I like it a lot, it will be a lot of work, but it can help a huge number of players, count on my help, in case you need something.
Nice to get your support,
I would like to have some additional price check for additional tests
just to see if the algorithm is more reliable.

Here a github for the project I created some basic element just for the beginning
https://github...

The good side of github is that is possible to keep track of every changement, it makes things more transparent.
If you want to help in the development of the project you can register in github and send me your username by PM.
I think that is the basic but i will think in a better organization system and will update the github.



 

Jinji

PWO's Resident Gengar
Staff member
Administrator
Joined
Aug 15, 2011
Messages
7,412
Points
113
Website
jinji.gamescodex.net
I struggle to understand any of this, but anything that helps players understand the value of their Pokémon is a very useful tool and I applaud the effort you are making here ^^
 

Nshims

New Member
Joined
May 28, 2014
Messages
227
Points
18
I struggle to understand any of this, but anything that helps players understand the value of their Pokémon is a very useful tool and I applaud the effort you are making here ^^


Thanks.
Yes, but for now still in development and will be hard to go in detail and explain everything.

In not very long time I intend to release a first functional version,
but for the moment I am still working on the graphical interface.

For the moment I thought about continuing with seel,
the idea is to try to have as much data as possible,
I am thinking in particular of pokemon that players have already captured
(if people want to share them obviously),
then ask willingly players who are good price check to assign prices to the different pokémons.

Then i can run some training on this data for tests.
Once the graphical interface is ready this will potentially represent the first pokémon that the price can be checked.
 

Prof.Rygar

Youngster
Joined
Jan 2, 2014
Messages
497
Points
63
I am happy to see this in production. This is likely something that will take many years to complete, but is well worth the effort. There's 100s of pokemon currently released into the game, do you have a plan to speed things up? Like, after you teach it to predict one pokemon, you can put in the max and min values and it will respond the same way to the rest of them?
 
Top