CAPFO - Consortium Apprentissage Expérientiel Francophone de l'Ontario
CAPFO - Consortium Apprentissage Expérientiel Francophone de l'Ontario
Se connecter S'inscrire

Machine Learning Capstone Project

CSML1030
Fermé
Contact principal
York University - School of Continuing Studies
York University - School of Continuing Studies
Cecilia Ying
Cecilia Ying
Machine Learning Certification Instructor
(0)
1
Chronologie
  • juillet 30, 2020
    Début de expérience
  • septembre 14, 2020
    Fin de expérience
Expérience
7/8 match de projet
Dates fixées par le expérience
Entreprises privilégiées
N'importe où
Any
N'importe qu'elle industrie

Portée de Expérience

Catégories
Technologie de l'information Analyse des données
Compétences
python analytic problem solving modelling machine learning big data
Objectifs et capacités de apprenant.es

Do you have a business problem that you'd like to solve with data? Do you want to make smart predictions about your customers? In this project, students in the Machine Learning Capstone course will address a problem of your choosing by applying analytics models, methodologies, and tools learned in their program. Teams will work on an end-to-end machine learning solution, from problem formulation to deployment. By the end of the course, a data product will be delivered to your organization.

Apprenant.es

Apprenant.es
Formation continue
Tout niveau
19 apprenant.es dans le programme
Projet
50 heures par apprenant.e
Les apprenant.es s'auto-attribuent
Équipes de 3
Résultats et livrables attendus

Students will deliver a final solution for the challenge defined by the organization:


  • The solution will include a product, all the codes and supplementary materials, as well as a comprehensive report on their findings and details of the technical solution.
  • Students will present final solutions and recommendations to representative(s) from your organization.
  • If applicable, future collaborative work between students and your organization will be determined mutually.
Chronologie du projet
  • juillet 30, 2020
    Début de expérience
  • septembre 14, 2020
    Fin de expérience

Exemples de projets

Beginning in mid-July, student-consultants in groups of four will spend ~200 hours per team performing a thorough investigation of data sets to address a business problem or opportunity of your choosing.


You can provide internal data, or ask that students leverage open source data to address the problem.


Tools such as Python and Tableau will be leveraged for data modelling, machine learning, and visualization.


When they start this course, students will have learned advanced techniques in machine learning, programming, and big data tools, and will be able to leverage open-source tools such as python or R, and machine learning libraries such as scikit-learn and Keras.


Students will execute the following steps during this course to solve a machine learning problem and provide a solution to your organization:


1. Research and frame an analytical problem, and implement a machine learning solution to the challenge faced by your organization.

2. Manage the workflow for a machine learning pipeline/solution based on the best in-class practices in industry, taught during the course and tracked through the project.

3. Author a technical document/report for your organization that gives an in-depth overview into the problem and the technical solution


Potential business challenges/opportunities might include, but are not limited to:

  • Predicting a customer's lifetime value
  • Text or numeric data classification to help solve a business problem
  • Recommendation engines
  • Fraud detection
  • ...and many more

Critères supplé mentaires pour entreprise

Les entreprises doivent répondre aux questions suivantes pour soumettre une demande de jumelage pour cette expérience:

  • Q1 - Case à cocher
    Be available to attend the final presentation day (in-person or remote), and provide feedback to students on their final solution/product.
  • Q2 - Case à cocher
    Provide feedback on the students' proposal submitted early in the course.
  • Q3 - Case à cocher
    Provide a dedicated contact who is available to answer periodic emails or phone calls over the duration of the project to address students' questions.
  • Q4 - Case à cocher
    Share data sets for students to analyze, OR ask that they work with open-source data to address your business problem (i.e. customer sentiment on social platforms)
  • Q5 - Case à cocher
    Be available for a quick phone call with the instructor to initiate your relationship and confirm your scope is an appropriate fit for the course.