Skip to main content

A poc for learning in a community.

Project description

Community Learning

Ziel ist es mit diesem kleine PoC aufzuzeigen wie mit Hilfe von Federated Learning bessere Prognose erzielt werden können.

Hier ein Auszug von der Kaggle Website

In this competition, you are provided with 1.5 years of customers behavior data from Santander bank to predict what new products customers will purchase. The data starts at 2015-01-28 and has monthly records of products a customer has, such as "credit card", "savings account", etc. You will predict what additional products a customer will get in the last month, 2016-06-28, in addition to what they already have at 2016-05-28. These products are the columns named: ind_(xyz)_ult1, which are the columns #25 - #48 in the training data. You will predict what a customer will buy in addition to what they already had at 2016-05-28.

Installation

Vorgehen PoC

Um den Usecase möglichst realistisch zu gestalten, gehen wir wie folgt vor:

Variante 1:

  1. Daten bereitstellen und bereinigen: Hierzu werden wir das Datenset so aufteilen, dass je ein Datenset pro Bank entsteht. Dazu werden wir ein geografisches Attribut hernehmen. Danach werden die Daten nochmals im Verhältnis 80/20 aufgeteilt in ein Train- und Testset (data_bank1_train, data_bank1_test, data_bank2_train, data_bank2_test).
  2. Baseline Modelle trainiern: Pro Bank werden wir einen GradientBoost Algorithmus trainieren mit deren Default-Einstellungen. Dadurch erhaltne wir 2 Modelle (model_bank1 und model_bank2)
  3. Ensemble Predictions: In diesem Schritt werden wir die Resultate von model_bank1 und model_bank2 kombinieren.
  • model_bank1 und model_bank2 wird mit den data_bank1_test gefüttert und eine gemeinsame Prediction erstellt.
  • model_bank1 und model_bank2 wird mit den data_bank2_test gefüttert und eine gemeinsame Prediction erstellt.
  1. Auswertung:: Um festzustellen ob das Ensemble eine Mehrwert bringt werden folgende Resultate verglichen.
  • model_bank1(data_bank1_test) vs ensemble(model_bank1(data_bank1_test), model_bank2(data_bank1_test)
  • model_bank2(data_bank2_test) vs ensemble(mdoel_bank2(data_bank1_test), model_bank2(data_bank2_test)

How to use

Fill me in please! Don't forget code examples:

1+1
2

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

community_learning-0.0.2.tar.gz (10.4 kB view details)

Uploaded Source

Built Distribution

community_learning-0.0.2-py3-none-any.whl (9.5 kB view details)

Uploaded Python 3

File details

Details for the file community_learning-0.0.2.tar.gz.

File metadata

  • Download URL: community_learning-0.0.2.tar.gz
  • Upload date:
  • Size: 10.4 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/3.1.1 pkginfo/1.5.0.1 requests/2.23.0 setuptools/45.2.0.post20200210 requests-toolbelt/0.9.1 tqdm/4.43.0 CPython/3.7.1

File hashes

Hashes for community_learning-0.0.2.tar.gz
Algorithm Hash digest
SHA256 4aabe91d1ec4c9e9dc0f36f95a8e39985151fa0f6329e86d3942500d98b09e6d
MD5 b4c9428009a48762c1805dfbb483dae4
BLAKE2b-256 7567aa1d70b58e34d3b9aa8ebcaf76464d4831361a570acb26b24542eef6d069

See more details on using hashes here.

File details

Details for the file community_learning-0.0.2-py3-none-any.whl.

File metadata

  • Download URL: community_learning-0.0.2-py3-none-any.whl
  • Upload date:
  • Size: 9.5 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/3.1.1 pkginfo/1.5.0.1 requests/2.23.0 setuptools/45.2.0.post20200210 requests-toolbelt/0.9.1 tqdm/4.43.0 CPython/3.7.1

File hashes

Hashes for community_learning-0.0.2-py3-none-any.whl
Algorithm Hash digest
SHA256 df7536616f35cb12b21957b7410991f151be5547d30ee9fe9827ca62bdbb2495
MD5 67c252401fe95696f23c283be0448914
BLAKE2b-256 46838448202da5ea6b9584b551990154d25f887607f09239529cfcb297c2dff5

See more details on using hashes here.

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page