Coder Social home page Coder Social logo

yogar81 / estimatingturnover_epflexts Goto Github PK

View Code? Open in Web Editor NEW
0.0 1.0 1.0 3.6 MB

My Capstone Project for the programme "Applied Datascience: Machine Learning" at the EPFL Extension School

Jupyter Notebook 100.00%
data-science machine-learning turnover epfl-ext-school statistics

estimatingturnover_epflexts's Introduction

Estimating Turnover in Retail trade

Capstone project for the program "Advanced Data Science: Machine Learning" of the EPFL Extension School

The Retail Trade Turnover Statistics (DHU) is a monthly economic statistic by the Federal Statistical Office (FSO) describing the evolution of turnover in retail trade at the national level. The survey population comprises all enterprises active in retail trade which are domiciled in Switzerland. Large and medium enterprises are surveyed exhaustively, small enterprises are surveyed randomly. The sample consists of around 4000 enterprises. Large enterprises are surveyed each month, the others four times per year, when monthly data are collected. To be able to publish representative results every month, data for three months are collected with one questionnaire for small and medium enterprises, but shifted by zero, one or two month for the three sub-samples. More information can be found on the FSO website: www.dhu.bfs.admin.ch

Goal of this project

At the time of the calculation of the results, not all enterprises have responded to the survey. Furthermore, the data users wish first estimations even earlier. Therefore, the goal of this project is to find methods to estimate the turnover of a given enterprise for a given month by using the information available from other respondents and the past.

Organisation

This project is split in 3 parts:

  • Data Preparation
  • Data Exploration
  • Machine Learning

In the Machine Learning part, 4 models are tested and tuned:

  • Ridge Regression
  • kNN Regression
  • RandomForest Regression
  • Clustering (k-Means)

The project contains the following jupyter notebooks:

  • 1_DataPreparation
  • 2_DataExploration
  • 3.1_ML_Preparation
  • 3.2_ML_Ridge
  • 3.3_ML_kNN
  • 3.4_ML_RandomForest
  • 3.5_ML_Clustering
  • 3.6_ML_Results

estimatingturnover_epflexts's People

Contributors

yogar81 avatar

Watchers

 avatar

Forkers

econmaett

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.