topical media & game development
recommender economy
cross sale -- users who bought A also bought B
up sale -- if you buy A and B together ...
recommender model
U = user
I = item
B = behavior
R = recommendation
F = feature
observations --
U \* I \* B
recommendations --
U \* I
B
= [ time = 20sec, rating = r ]
F
= [ artist = rembrandt, topic = portrait ]
R
= [ artist(rembrandt) = r, topic(portrait) = r ]
A
= [
p_{1}, p_2
, ... ] where
p_{k}
= [
f_1 = v_1
,
f_2 = v_2
,
...
]
with as an example
A_{nightwatch}
= [ artist=rembrandt, topic=group ]
A_{guernica}
= [ artist=picasso, topic=group ]
...
users, artworks and properties
distance metric
d(x,y) = d(y,x)
d(x,y) <= d(x,z) + d(z,y)
d(x,x) = 0
dimension(s)
positive vs negative
individual vs community/collaborative
feature-based vs item-based
interpretation(s)
neutral interpretation -- use
d(s_{n}, a_{k}) < d(s_{n}, s_{n+1} )
positive interpretation -- increase
w(feature(a_{k}))
negative interpretation -- decrease
w(feature(s_{n+1}))
