Search Results for author: Kasun Bandara

Found 13 papers, 8 papers with code

Day-ahead regional solar power forecasting with hierarchical temporal convolutional neural networks using historical power generation and weather data

no code implementations4 Mar 2024 Maneesha Perera, Julian De Hoog, Kasun Bandara, Damith Senanayake, Saman Halgamuge

In this work, we propose two deep-learning-based regional forecasting methods that can effectively leverage both types of time series (aggregated and individual) with weather data in a region.

Time Series

Handling Concept Drift in Global Time Series Forecasting

1 code implementation4 Apr 2023 Ziyi Liu, Rakshitha Godahewa, Kasun Bandara, Christoph Bergmeir

Handling concept drift in forecasting is essential for many ML methods in use nowadays, however, the prior work only proposes methods to handle concept drift in the classification domain.

Time Series Time Series Forecasting

A Hybrid Statistical-Machine Learning Approach for Analysing Online Customer Behavior: An Empirical Study

no code implementations1 Dec 2022 Saed Alizami, Kasun Bandara, Ali Eshragh, Foaad Iravani

While most mere machine learning methods are plagued by the lack of interpretability in practice, our novel hybrid approach will address this practical issue by generating explainable output.


Multi-Resolution, Multi-Horizon Distributed Solar PV Power Forecasting with Forecast Combinations

1 code implementation22 Jun 2022 Maneesha Perera, Julian De Hoog, Kasun Bandara, Saman Halgamuge

We propose a forecast combination approach based on particle swarm optimization (PSO) that will enable a forecaster to produce accurate forecasts for the task at hand by weighting the forecasts produced by individual models.

Ensembles of Localised Models for Time Series Forecasting

1 code implementation30 Dec 2020 Rakshitha Godahewa, Kasun Bandara, Geoffrey I. Webb, Slawek Smyl, Christoph Bergmeir

With large quantities of data typically available nowadays, forecasting models that are trained across sets of time series, known as Global Forecasting Models (GFM), are regularly outperforming traditional univariate forecasting models that work on isolated series.

Clustering Time Series +1

Global Models for Time Series Forecasting: A Simulation Study

1 code implementation23 Dec 2020 Hansika Hewamalage, Christoph Bergmeir, Kasun Bandara

Our experiments demonstrate that when trained as global forecasting models, techniques such as RNNs and LGBMs, which have complex non-linear modelling capabilities, are competitive methods in general under challenging forecasting scenarios such as series having short lengths, datasets with heterogeneous series and having minimal prior knowledge of the patterns of the series.

Time Series Time Series Forecasting

Improving the Accuracy of Global Forecasting Models using Time Series Data Augmentation

no code implementations6 Aug 2020 Kasun Bandara, Hansika Hewamalage, Yuan-Hao Liu, Yanfei Kang, Christoph Bergmeir

Forecasting models that are trained across sets of many time series, known as Global Forecasting Models (GFM), have shown recently promising results in forecasting competitions and real-world applications, outperforming many state-of-the-art univariate forecasting techniques.

Data Augmentation Dynamic Time Warping +3

Towards Accurate Predictions and Causal 'What-if' Analyses for Planning and Policy-making: A Case Study in Emergency Medical Services Demand

no code implementations25 Apr 2020 Kasun Bandara, Christoph Bergmeir, Sam Campbell, Deborah Scott, Dan Lubman

Emergency Medical Services (EMS) demand load has become a considerable burden for many government authorities, and EMS demand is often an early indicator for stress in communities, a warning sign of emerging problems.

Time Series Time Series Analysis

LSTM-MSNet: Leveraging Forecasts on Sets of Related Time Series with Multiple Seasonal Patterns

3 code implementations10 Sep 2019 Kasun Bandara, Christoph Bergmeir, Hansika Hewamalage

Generating forecasts for time series with multiple seasonal cycles is an important use-case for many industries nowadays.

Time Series Time Series Analysis

Recurrent Neural Networks for Time Series Forecasting: Current Status and Future Directions

3 code implementations2 Sep 2019 Hansika Hewamalage, Christoph Bergmeir, Kasun Bandara

Recurrent Neural Networks (RNN) have become competitive forecasting methods, as most notably shown in the winning method of the recent M4 competition.

Time Series Time Series Forecasting

Sales Demand Forecast in E-commerce using a Long Short-Term Memory Neural Network Methodology

1 code implementation13 Jan 2019 Kasun Bandara, Peibei Shi, Christoph Bergmeir, Hansika Hewamalage, Quoc Tran, Brian Seaman

Since the product assortment hierarchy in an E-commerce platform contains large numbers of related products, in which the sales demand patterns can be correlated, our attempt is to incorporate this cross-series information in a unified model.

Time Series Time Series Analysis

Forecasting Across Time Series Databases using Recurrent Neural Networks on Groups of Similar Series: A Clustering Approach

3 code implementations9 Oct 2017 Kasun Bandara, Christoph Bergmeir, Slawek Smyl

In particular, in terms of mean sMAPE accuracy, it consistently outperforms the baseline LSTM model and outperforms all other methods on the CIF2016 forecasting competition dataset.

Benchmarking Clustering +3

Cannot find the paper you are looking for? You can Submit a new open access paper.