Institutional Repository of Vilnius University
Logistikos sektoriaus įmonių veiklos vertinimas /
Abstract
dc:descriptionThis bachelor thesis evaluates the performance of two Lithuanian logistics companies using key performance indicators (KPI), correlation analysis, K‐means clustering, and time series forecas‐ ting methods. The aim of the thesis is to assess and compare the performance results of Company A and Company B based on financial and relative efficiency indicators. The study analyses actual operational data of two Lithuanian logistics companies obtained from a business analytics firm. The analysis of Company A covers 14,711 trips over the period 2015–2022, while Company B covers over 300 thousand trips over the period 2022–2024. The analysis was performed using RStudio. The study calculates key absolute indicators: revenue, costs, profit and distance travelled, as well as rela‐ tive efficiency indicators: revenue per kilometre, costs per kilometre, profit per kilometre and profit margin. Descriptive statistics, outlier analysis, correlation analysis, K‐means clustering, and cluster count validation using the elbow method and silhouette score were applied. To reduce the impact of differing data periods on the company comparison, a forecast of Company A’s profit per kilomet‐ re was also generated for Company B’s data period using an ARIMA(2,1,2) model. The results show that Company B demonstrates higher profitability across the analysed relative indicators. Compa‐ ny B’s average revenue per kilometre was 1.43 EUR/km, compared to 1.05 EUR/km for Company A. Company B also had a higher profit margin of 0.64, versus 0.53 for Company A. K‐means clustering identified three distinct efficiency groups in both companies. Company A had a low‐efficiency cluster where trips were on average unprofitable, whereas all clusters in Company B remained profitable. The forecast results indicate that Company B’s actual profit per kilometre (averaging 1.00 EUR/km) consistently exceeded not only Company A’s forecasted mean (0.585 EUR/km) but also the upper bound of the 95 Keywords: logistics performance evaluation, key performance indicators, correlation analysis, K‐ means clustering, time series forecasting, ARIMA, operational efficiency.
Degree
thesis:*- Grantor dc:publisher
- Institutional Repository of Vilnius University
- Year dc:date
- 2026
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Antulytė, Gintarė,
Rights
dc:rights- Statement dc:rights
-
- info:eu-repo/semantics/openAccess
- Language dc:language
- lit
Identifiers
dc:identifier.*- Repository record dc:identifier
- https://repository.vu.lt/VU:ELABAETD308332982&prefLang=en_US