| Title |
Taksi maršrutų didelio duomenų kiekio apdorojimas ir analizė / |
| Translation of Title |
Taxi trip big data processing and analysis. |
| Authors |
Dundulis, Arnas |
| Full Text |
|
| Pages |
61 |
| Keywords [eng] |
taxi trip ; big data ; clustering ; segmentation |
| Abstract [eng] |
Analyzing taksi trip data one of the criteria that allows drivers to increase their income is the whether the rider leaves a tip for the trip. Since this is not mandatory the ability to determine if a tip will be given after a ride is sought after. One of the ways to increase the accuracy of such a prediction is data grouping by some criteria. This article will explore the social aspects associated with gratuity and describe the ways in which taxi trip data can be clustered and classified. K-means method will be used for clusterization and classification accuracy will be compared between decision tree, random forest and neural network methods. |
| Dissertation Institution |
Kauno technologijos universitetas. |
| Type |
Master thesis |
| Language |
Lithuanian |
| Publication date |
2017 |
