All Products
Search
Document Center

Platform For AI:prediksi ALS

Last Updated:Mar 07, 2026

Menghitung skor pengguna dan item berdasarkan hasil faktorisasi matriks ALS dari metode User-Item Collaborative Filtering.

Batasan

Komponen ini mendukung mesin komputasi MaxCompute dan Flink.

Konfigurasikan parameter komponen

  • Port Input

    Input port (kiri ke kanan)

    Tipe data

    Komponen hulu yang direkomendasikan

    Wajib

    User factor table

    None

    ALS Matrix Factorization

    Yes

    Item factor table

    None

    ALS Matrix Factorization

    Yes

    Input data to be scored

    None

    Yes

  • Parameter Komponen

    Tab

    Parameter

    Deskripsi

    Field Settings

    User column

    Nama kolom ID pengguna dalam sumber data input. Harus bertipe BIGINT.

    Item column

    Nama kolom item dalam sumber data input. Harus bertipe BIGINT.

    Parameter Settings

    Prediction result column name

    Nama kolom dalam tabel output untuk menyimpan hasil scoring.

    Output table lifecycle

    Lifecycle dari tabel output.

    Execution Tuning

    Number of workers

    Nilai harus berada dalam rentang 1 hingga 9999.

    Memory size per worker

    Nilai harus berada dalam rentang 1024 MB hingga 64 × 1024 MB.

  • Port keluaran

    Output port (kiri ke kanan)

    Tipe data

    Komponen hilir

    Scoring result table

    None

    None

Contoh penggunaan

Tabel faktor pengguna dan item untuk scoring:

  • Output user factor table

    user_id

    factors

    8528750

    [0.026986524,0.03350178,0.03532385,0.019542359,0.020429865,0.02046867,0.022253247,0.027391396,0.018985065,0.04889483]

    282500

    [0.116156064,0.07193632,0.090851225,0.017075706,0.025412979,0.047022138,0.12534861,0.05869226,0.11170533,0.1640192]

    4895250

    [0.038429666,0.061858658,0.04236993,0.055866677,0.031814687,0.0417443,0.012085311,0.0379342,0.10767074,0.028392972]

    ...

    ...

  • Output item factor table

    item_id

    factors

    24601

    [0.0063337763,0.026349949,0.0064828005,0.01734504,0.022049638,0.0059205987,0.008568814,0.0015981696,0.0,0.013601779]

    26699

    [0.0027524426,0.0043066847,0.0031336215,0.00269448,0.0022347474,0.0020477585,0.0027995422,0.0025390312,0.0033011117,0.003957773]

    20751

    [0.03902271,0.050952066,0.032981463,0.03862796,0.048720762,0.027976315,0.02721664,0.018149626,0.0149896275,0.026251089]

    ...

    ...

Scoring result table:

user_id

item_id

pred

19500

143

1.882628425846633E-4

19500

2610

1.1106864974408381E-4

19500

2655

8.975836536251336E-6

19500

3190

1.6171501181361236E-4

19500

3720

2.3276544959571766E-4

19500

5254

2.420645481606698E-4