Recommendation.jl: Building Recommender Systems in Julia

Lightning Talk @ JuliaCon 2019

https://pretalx.com/juliacon2019/talk/FFXKCX/

Video: https://www.youtube.com/watch?v=kC8LKQ_YjyM

Transcript

1. Recommenda)on.jl
   Building Recommender Systems in Julia
   Takuya Kitazawa
   

   View Slide

2. julia> using Pkg; Pkg.add(“Recommendation”)
   github.com/takuti/Recommendation.jl
   

   View Slide

3. mutable struct Event
   user::Int
   item::Int
   value::Float64
   end
   item
   user
   value
   Explicit: Ra)ng feedback
   Implicit: Unary feedback
   

   View Slide

4. • User-item matrix:
   • Series of events for more users/items:
   Data := User-Item Interac)ons
   using Recommendation
   using SparseArrays
   data = DataAccessor(sparse([1 0 0; 4 5 0]))
   n_user, n_item = 5, 10
   events = [Event(1, 2, 1.0), Event(3, 2, 1.0), Event(2, 6, 4.0)]
   data = DataAccessor(events, n_user, n_item)
   Explicit
   ra)ngs
   

   View Slide

5. recommender = MostPopular(data)
   build!(recommender)
   recommend(recommender, 4, 2, collect(1:n_item))
   # for user#4, pick top-2 from all items
   Common interfaces
   Recommenda5on algorithm
   data
   

   View Slide

6. • Coun)ng frequency of…
   Most frequently co-observed items with i_ref
   Most frequently observed items
   • Weigh)ng items by…
   % of observed values that are greater than th
   Mean of observed values across all users
   Mean of observed values across all items
   Quick math… Non-Personalized Baseline Recommender
   CoOccurrence(data, i_ref)
   MostPopular(data)
   ThresholdPercentage(data, th)
   UserMean(data)
   ItemMean(data)
   

   View Slide

7. Bit more… Collabora)ve Filtering (CF)
   UserKNN(data, k)
   ItemKNN(data, k)
   

   View Slide

8. And more! SVD & Matrix Factoriza)on (MF)
   SVD(data, k)
   recommender = MF(data, k)
   build!(recommender, learning_rate=1e-3, max_iter=100)
   

   View Slide

9. Evalua)on
   recall = cross_validation(
   5, # N-fold
   Recall, # Metric
   5, # Top-k recommendation
   MostPopular, # Recommender
   data, # Data Accessor
   args… # Hyperparameters
   )
   Ra5ng metric:
   - MAE
   - RMSE
   Ranking metric:
   - AUC
   - Mean Average Precision
   - Mean Percen)le Rank
   - NDCG
   - Precision
   - Recall
   - Reciprocal Rank
   

   View Slide

10. Recommender Systems + Julia =
    • Vector/matrix-friendly syntax
    • High simplicity and modularity
    • Efficient numerical compu)ng, especially for matrices
    • Good ecosystem surrounding mathema)cal tools
    - Recommender system is not only about ML
    

    View Slide

11. Recommender Systems + Julia = …
    • Integra)on with real-world applica)ons
    - Con)nuously observed new events
    - Scheduled model update and recommenda)on
    - Can be real-)me
    - Scalability
    

    View Slide

12. Keep minimal under…
    But make customizable
    

    View Slide

13. using LinearAlgebra
    using LowRankApprox
    struct PartialQR <: Recommender
    data::DataAccessor
    rank::Int
    Q::AbstractMatrix
    R::AbstractMatrix
    p::AbstractVector
    function PartialQR(data::DataAccessor, rank::Int)
    n_user, n_item = size(data.R)
    Q = matrix(n_user, rank)
    R = matrix(rank, n_item)
    p = vector(n_item, Int)
    new(data, rank, Q, R, p)
    end
    end
    JuliaMatrices/LowRankApprox.jl
    (Hyper-)Parameters
    

    View Slide

14. isbuilt(recommender::PartialQR) = isfilled(recommender.Q)
    function build!(recommender::PartialQR)
    # NaNs are filled by zeros for now
    R = copy(recommender.data.R)
    R[isnan.(R)] .= 0
    F = pqrfact(R, rank=recommender.rank)
    recommender.Q[:] = F.Q[:]
    recommender.R[:] = F.R[:]
    recommender.p[:] = F.p[:]
    end
    function Recommendation.predict(recommender::PartialQR, u::Int, i::Int)
    check_build_status(recommender)
    dot(recommender.Q[u, :], recommender.R[:, recommender.p][:, i])
    end
    Low rank approxima)on
    

    View Slide

15. julia> using Pkg; Pkg.add(“Recommendation”)
    github.com/takuti/Recommendation.jl
    

    View Slide