Build an Artificial Neural Network to Predict Customer Churn | Step-by-Step Tutorial

Поделиться
HTML-код
  • Опубликовано: 12 янв 2025

Комментарии • 8

  • @joguns8257
    @joguns8257 Месяц назад

    Superb illustration👍

  • @TheMaxKids
    @TheMaxKids 4 месяца назад +2

    Absolutely the best video on the topic I've seen yet. Thank you.

  • @0.4sks19
    @0.4sks19 3 месяца назад +1

    where can i find your documentation code?

  • @abdulsalamaliyu2563
    @abdulsalamaliyu2563 4 месяца назад

    Please how do you get the numeric representation of datas that you use to predict churn ?

    • @TheOpenSourceChannel
      @TheOpenSourceChannel  4 месяца назад

      Please check the video at 4:30
      There are two steps to get the numeric representation of data.
      Label Encoding: It converts categorical data into numerical labels. For example Female become 0 and Male become 1.
      One-Hot Encoding: It creates new binary features for each category to represent its independent effects. For example France become [1, 0, 0], Spain become [0, 0, 1], and Germany become [0, 1, 0].

  • @srishrachamalla9607
    @srishrachamalla9607 4 месяца назад

    hey i have a qn should i use ML or DL when these kind of problems statements used?

    • @TheOpenSourceChannel
      @TheOpenSourceChannel  4 месяца назад +1

      If you have a smaller dataset, you should start with an ML model. It is beginner friendly as you can use established ML algorithms.
      If you have a large and complex dataset, and want to learn complex features and relationships from your data, then DL might be worth exploring. Because DL requires more computational resources and complex to implement.