Inspiration

The lack of use of sentimental data in the world of Decentralized finance. Fundamental and Sentimental data is the driver of Crypto/NFT price action. With Stackon, users can make calculated decisons about their digital assets using predictions from Stackon Hero model.

What it does

Millions of crypto adopters are in desperate need of a tool that can predict future prices of cryptocurrencies, NFTs and digital assets so they know how to manage their assets and prevent being a victim when price crashes. Simply, Stackon is a neural network decentralized application that predicts the future price of NFTs, Digital assets and Cryptocurrencies by using historical and sentimental price action data. The Stackon model was tested to have an accuracy of 97%.

How we built it

We trained our model using neural networks which got connected to the Application Programming Interface using customly built response hooks to POST and GET data from the model. Being a decentralized application, we deployed Stackon on the Blockchain network which currently is one of the fastest growing decentralized networks with the ERC-71 Protocol to connect to users' wallet and also GET assets information to be predicted by the Stackon Model.

Challenges we ran into

A whole lot, since this is a new dispensation of data usage I ran into data pre-processing issues with limited time because i became aware and joined the hackathon just a week before deadline. Even, the deployed site unexpectedly failed so i'm still working on debugging it as of this moment of submission (which is few minutes to deadline; lol.

Accomplishments that we're proud of

The neural network as an accuracy score of 97% and I'm proud that i was able to build this 1 week to the end of the hackathon as i wasn't aware earlier. Also, most API providers i needed to get historical data from delayed so i had to create a detailed data set from scratch using affiliated historical data. The neural network has an accuracy score of 97% and that we are highly proud of as many neural networks do not exceed accuracy limits of 70%- 80%

What we learned

More sentimental price action theories and how machine & deep learning and transform the world of De-Fi.

What's next for Stackon

Well, Stackon will surely go live and will have more integrations and features and atlas will be available for all. Even I can't wait to see how Stackon Dr Market will transform the industry.

Share this project:

Updates