Nico.cast🐱 pfp
Nico.cast🐱
@n
Working on a ML model which will output an 'address score' similar to how credit scores work (~low is 300-500, mid 500-650, high 650+) some interesting data: me: 529.52 @shoni.eth: 567.79 @cassie: 685.06 @jc: 698.19 @dwr.eth: 663.29 @dcposch.eth: 752.81
25 replies
0 recast
0 reaction

🌹 zach harris 🥀 pfp
🌹 zach harris 🥀
@zachharris.eth
Would it also have the same bias that systematically under-represents minority groups like FICO?
1 reply
0 recast
0 reaction

Nico.cast🐱 pfp
Nico.cast🐱
@n
I hear you, I have worked in fintech most of my life and agree FICO score can be very biased The score depends on the sum of weights and normalization of dozens of on-chain criteria. My thoughts on eliminating biases: we need a decentralized scoring system where different identities can report their own member score.
1 reply
0 recast
0 reaction

Nico.cast🐱 pfp
Nico.cast🐱
@n
For example: your base score is 700, as predicted by the ML model Farcaster can report your address score to be 750, if you are an active caster and engaged member And then Opensea, Lens, and other parties can report different scores The final score can be computed by any aggregators. Better system than Equifax +2.
1 reply
0 recast
0 reaction