Skip to content

2. Dataset

Arif Agustyawan edited this page Dec 24, 2023 · 1 revision

The engine relies on a comprehensive dataset sourced from a CSV file specified in the config.conf configuration. The dataset comprises essential information such as customer IDs, product IDs, purchase IDs, and timestamps, forming the foundation for training the predictive model. Here are the dataset format used to train the model

purchase_id purchase_date customer_id product_id
PR100 2023-06-01 CU139 product8
PR101 2023-06-01 CU143 product4
PR102 2023-06-01 CU148 product7
PR103 2023-06-01 CU184 product1
PR104 2023-06-02 CU120 product5
PR105 2023-06-02 CU169 product9
PR106 2023-06-03 CU200 product4
PR107 2023-06-04 CU128 product5
PR108 2023-06-04 CU154 product2
PR109 2023-06-05 CU108 product6

Clone this wiki locally