You are viewing a single comment's thread from:

RE: Introducing the Steem Recommendation Page

in #steem8 years ago (edited)

Learning conditional preference networks could be used to suggest how people should vote over time depending on if Steemit has the computation capacity to implement it. It may be possible to suggest based on patterns and prediction algorithms which votes make the most economic sense. A/B testing can be used in order to tease out useful information from noisy data samples.

References
1.Learning conditional preference network from noisy samples using hypothesis testing

Coin Marketplace

STEEM 0.18
TRX 0.13
JST 0.029
BTC 57616.20
ETH 3030.92
USDT 1.00
SBD 2.25