Machine learning is a topic that is being used in more areas. More companies want to take advantage of this to be able to improve their sales models. The aim of the project was to develop a forecasting tool as this could result in a possible increased profit for the customer. Forecasting takes place at the Amount data point using the two machine learning models random decision tree and recurrent neural network. The random decision tree model only predicts the data point while the recurrent neural network model predicts the data point with the account of L. The data was investigated with the exploratory data analysis model to investigate relationships, find anomalies and designate data points, and then be used in the machine learning models. The result of the work is that the two models achieve an average error for forecasting that is within the client’s acceptable limits.
| Identifer | oai:union.ndltd.org:UPSALLA1/oai:DiVA.org:kau-78151 |
| Date | January 2020 |
| Creators | Johan, Pedersen, Rebecka, Alfredsson |
| Publisher | Karlstads universitet, Institutionen för matematik och datavetenskap (from 2013), Karlstads universitet, Institutionen för matematik och datavetenskap (from 2013) |
| Source Sets | DiVA Archive at Upsalla University |
| Language | Swedish |
| Detected Language | English |
| Type | Student thesis, info:eu-repo/semantics/bachelorThesis, text |
| Format | application/pdf |
| Rights | info:eu-repo/semantics/openAccess |
Page generated in 0.0167 seconds