Estimating Task Completion Times for Network Rollouts using Statistical Models within Partitioning-based Regression Methods

TL;DR

This paper introduces a partition-based regression approach using statistical models for forecasting task completion times in telecommunications network rollouts, improving accuracy and interpretability over existing methods.

Contribution

It presents a novel partition-based regression model that combines data-driven statistical methods within each partition for better forecasting accuracy and interpretability.

Findings

Achieves competitive or superior performance compared to Gradient Boosting.

Effective for both short and long-range forecasts.

Requires less model complexity than gradient boosting approaches.

Abstract

This paper proposes a data and Machine Learning-based forecasting solution for the Telecommunications network-rollout planning problem. Milestone completion-time estimation is crucial to network-rollout planning; accurate estimates enable better crew utilisation and optimised cost of materials and logistics. Using historical data of milestone completion times, a model needs to incorporate domain knowledge, handle noise and yet be interpretable to project managers. This paper proposes partition-based regression models that incorporate data-driven statistical models within each partition, as a solution to the problem. Benchmarking experiments demonstrate that the proposed approach obtains competitive to better performance, at a small fraction of the model complexity of the best alternative approach based on Gradient Boosting. Experiments also demonstrate that the proposed approach is effective for both short and long-range forecasts. The proposed idea is applicable in any context requiring time-series regression with noisy and attributed data.