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

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.


Comparing statistical and machine learning methods for time series forecasting in data-driven logistics – A simulation study

Many planning and decision activities in logistics and supply chain mana...

Mitigating Cold-start Forecasting using Cold Causal Demand Forecasting Model

Forecasting multivariate time series data, which involves predicting fut...

Do We Really Need Deep Learning Models for Time Series Forecasting?

Time series forecasting is a crucial task in machine learning, as it has...

GPSINDy: Data-Driven Discovery of Equations of Motion

In this paper, we consider the problem of discovering dynamical system m...

Ensemble Learning based Convexification of Power Flow with Application in OPF

This paper proposes an ensemble learning based approach for convexifying...

A Data-Driven Approach for Predicting Vegetation-Related Outages in Power Distribution Systems

This paper presents a novel data-driven approach for predicting the numb...

Finding the Best Partitioning Policy for Efficient Verification of Autonomous Systems at Runtime

The autonomous systems need to decide how to react to the changes at run...

Please sign up or login with your details

Forgot password? Click here to reset