Development of a sales forecasting software engine

Rodríguez López, Ignacio (2019). Development of a sales forecasting software engine. Proyecto Fin de Carrera / Trabajo Fin de Grado, E.T.S. de Ingenieros Informáticos (UPM), Madrid, España.

Description

Title: Development of a sales forecasting software engine
Author/s:
  • Rodríguez López, Ignacio
Contributor/s:
Item Type: Final Project
Degree: Grado en Ingeniería Informática
Date: June 2019
Subjects:
Faculty: E.T.S. de Ingenieros Informáticos (UPM)
Department: Lenguajes y Sistemas Informáticos e Ingeniería del Software
Creative Commons Licenses: Recognition - No derivative works - Non commercial

Full text

[thumbnail of TFG_IGNACIO_RODRIGUEZ_LOPEZ.pdf]
Preview
PDF - Requires a PDF viewer, such as GSview, Xpdf or Adobe Acrobat Reader
Download (2MB) | Preview

Abstract

La predicción de ventas es una de las aplicaciones más importantes del machine learning en las empresas en el mundo actual. En un mundo con una competitividad tan elevada, ser capaz de predecir las necesidades de tu empresa y poder tener la mayor cantidad de tiempo posible puede significar la diferencia entre el éxito y el fracaso. El problema es que existen gran cantidad de métodos, cada uno con sus ventajas e inconvenientes para poder lograrlo. En este documento se analizan varios de ellos, creando modelos para un conjunto de datos concreto y analizando los resultados. Finalmente, se incluye una pequeña implementación en Python del que se ha considerado como el mejor resultado.---ABSTRACT---Nowadays, sales forecasting is one of the most important machine learning applications used by companies. In such a competitive world, been able to predict the necessities of your company in order to get the maximum amount of time possible to take actions makes de the difference between the successful and the failure. The main problem is the vast amount of possibilities, each one with their own set of advantages and disadvantages. In this document, some of them are analyzed by creating models from a concrete dataset and analyzing the results. Finally, a simple Python implementation of the best option according to the testing, is provided.

More information

Item ID: 55761
DC Identifier: https://oa.upm.es/55761/
OAI Identifier: oai:oa.upm.es:55761
Deposited by: Biblioteca Facultad de Informatica
Deposited on: 11 Jul 2019 14:10
Last Modified: 11 Jul 2019 14:10
  • Logo InvestigaM (UPM)
  • Logo GEOUP4
  • Logo Open Access
  • Open Access
  • Logo Sherpa/Romeo
    Check whether the anglo-saxon journal in which you have published an article allows you to also publish it under open access.
  • Logo Dulcinea
    Check whether the spanish journal in which you have published an article allows you to also publish it under open access.
  • Logo de Recolecta
  • Logo del Observatorio I+D+i UPM
  • Logo de OpenCourseWare UPM