Search Results for author: Christoph Bergmeir

Found 40 papers, 21 papers with code

Adaptive Dependency Learning Graph Neural Networks

1 code implementation6 Dec 2023 Abishek Sriramulu, Nicolas Fourrier, Christoph Bergmeir

In this paper, we propose a hybrid approach combining neural networks and statistical structure learning models to self-learn the dependencies and construct a dynamically changing dependency graph from multivariate data aiming to enable the use of GNNs for multivariate forecasting even when a well-defined graph does not exist.

Time Series

RNN-BOF: A Multivariate Global Recurrent Neural Network for Binary Outcome Forecasting of Inpatient Aggression

no code implementations2 Dec 2023 Aidan Quinn, Melanie Simmons, Benjamin Spivak, Christoph Bergmeir

Psychometric assessment instruments aid clinicians by providing methods of assessing the future risk of adverse events such as aggression.

Time Series

On Forecast Stability

no code implementations26 Oct 2023 Rakshitha Godahewa, Christoph Bergmeir, Zeynep Erkin Baz, Chengjun Zhu, Zhangdi Song, Salvador García, Dario Benavides

To fill this gap, we propose a simple linear-interpolation-based approach that is applicable to stabilise the forecasts provided by any base model vertically and horizontally.

Local and Global Trend Bayesian Exponential Smoothing Models

no code implementations25 Sep 2023 Slawek Smyl, Christoph Bergmeir, Alexander Dokumentov, Xueying Long, Erwin Wibowo, Daniel Schmidt

This paper describes a family of seasonal and non-seasonal time series models that can be viewed as generalisations of additive and multiplicative exponential smoothing models, to model series that grow faster than linear but slower than exponential.

Time Series

Deep Active Audio Feature Learning in Resource-Constrained Environments

no code implementations25 Aug 2023 Md Mohaimenuzzaman, Christoph Bergmeir, Bernd Meyer

The scarcity of labelled data makes training Deep Neural Network (DNN) models in bioacoustic applications challenging.

Active Learning

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

SETAR-Tree: A Novel and Accurate Tree Algorithm for Global Time Series Forecasting

1 code implementation16 Nov 2022 Rakshitha Godahewa, Geoffrey I. Webb, Daniel Schmidt, Christoph Bergmeir

On the other hand, in the forecasting community, general-purpose tree-based regression algorithms (forests, gradient-boosting) have become popular recently due to their ease of use and accuracy.

regression TAR +2

Causal Effect Estimation with Global Probabilistic Forecasting: A Case Study of the Impact of Covid-19 Lockdowns on Energy Demand

no code implementations19 Sep 2022 Ankitha Nandipura Prasanna, Priscila Grecov, Angela Dieyu Weng, Christoph Bergmeir

We consider the impact of Covid-19 lockdowns on energy usage as a case study to evaluate the non-uniform effect of this intervention on the electricity demand distribution.

counterfactual Load Forecasting +1

FRANS: Automatic Feature Extraction for Time Series Forecasting

no code implementations15 Sep 2022 Alexey Chernikov, Chang Wei Tan, Pablo Montero-Manso, Christoph Bergmeir

Traditionally, features used in TSF are handcrafted, which requires domain knowledge and significant data-engineering work.

Dimensionality Reduction Meta-Learning +2

Forecast Evaluation for Data Scientists: Common Pitfalls and Best Practices

no code implementations21 Mar 2022 Hansika Hewamalage, Klaus Ackermann, Christoph Bergmeir

We elaborate on the different problematic characteristics of time series such as non-normalities and non-stationarities and how they are associated with common pitfalls in forecast evaluation.

Decision Making Time Series +1

LIMREF: Local Interpretable Model Agnostic Rule-based Explanations for Forecasting, with an Application to Electricity Smart Meter Data

no code implementations15 Feb 2022 Dilini Rajapaksha, Christoph Bergmeir

In order to explain the global model forecasts, we propose Local Interpretable Model-agnostic Rule-based Explanations for Forecasting (LIMREF), a local explainer framework that produces k-optimal impact rules for a particular forecast, considering the global forecasting model as a black-box model, in a model-agnostic way.

counterfactual Decision Making +2

NeuralProphet: Explainable Forecasting at Scale

1 code implementation29 Nov 2021 Oskar Triebe, Hansika Hewamalage, Polina Pilyugina, Nikolay Laptev, Christoph Bergmeir, Ram Rajagopal

NeuralProphet is a hybrid forecasting framework based on PyTorch and trained with standard deep learning methods, making it easy for developers to extend the framework.

Decision Making Philosophy +3

LoMEF: A Framework to Produce Local Explanations for Global Model Time Series Forecasts

no code implementations13 Nov 2021 Dilini Rajapaksha, Christoph Bergmeir, Rob J Hyndman

Global Forecasting Models (GFM) that are trained across a set of multiple time series have shown superior results in many forecasting competitions and real-world applications compared with univariate forecasting approaches.

Time Series Time Series Analysis

Monash Time Series Forecasting Archive

1 code implementation14 May 2021 Rakshitha Godahewa, Christoph Bergmeir, Geoffrey I. Webb, Rob J. Hyndman, Pablo Montero-Manso

Many businesses and industries nowadays rely on large quantities of time series data making time series forecasting an important research area.

Time Series Time Series Forecasting

Environmental Sound Classification on the Edge: A Pipeline for Deep Acoustic Networks on Extremely Resource-Constrained Devices

1 code implementation5 Mar 2021 Md Mohaimenuzzaman, Christoph Bergmeir, Ian Thomas West, Bernd Meyer

Significant efforts are being invested to bring state-of-the-art classification and recognition to edge devices with extreme resource constraints (memory, speed, and lack of GPU support).

Environmental Sound Classification Model Compression +2

Versatile and Robust Transient Stability Assessment via Instance Transfer Learning

no code implementations20 Feb 2021 Seyedali Meghdadi, Guido Tack, Ariel Liebman, Nicolas Langrené, Christoph Bergmeir

To support N-1 pre-fault transient stability assessment, this paper introduces a new data collection method in a data-driven algorithm incorporating the knowledge of power system dynamics.

Transfer Learning

SQAPlanner: Generating Data-Informed Software Quality Improvement Plans

1 code implementation19 Feb 2021 Dilini Rajapaksha, Chakkrit Tantithamthavorn, Jirayus Jiarpakdee, Christoph Bergmeir, John Grundy, Wray Buntine

Thus, our SQAPlanner paves a way for novel research in actionable software analytics-i. e., generating actionable guidance on what should practitioners do and not do to decrease the risk of having defects to support SQA planning.

MultiRocket: Multiple pooling operators and transformations for fast and effective time series classification

1 code implementation31 Jan 2021 Chang Wei Tan, Angus Dempster, Christoph Bergmeir, Geoffrey I. Webb

We propose MultiRocket, a fast time series classification (TSC) algorithm that achieves state-of-the-art performance with a tiny fraction of the time and without the complex ensembling structure of many state-of-the-art methods.

General Classification Time Series +2

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

Model selection in reconciling hierarchical time series

1 code implementation21 Oct 2020 Mahdi Abolghasemi, Rob J Hyndman, Evangelos Spiliotis, Christoph Bergmeir

However, when dealing with hierarchical time series, apart from selecting the most appropriate forecasting model, forecasters have also to select a suitable method for reconciling the base forecasts produced for each series to make sure they are coherent.

Model Selection Time Series +1

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

Simulation and Optimisation of Air Conditioning Systems using Machine Learning

no code implementations27 Jun 2020 Rakshitha Godahewa, Chang Deng, Arnaud Prouzeau, Christoph Bergmeir

In building management, usually static thermal setpoints are used to maintain the inside temperature of a building at a comfortable level irrespective of its occupancy.

BIG-bench Machine Learning Management

Seasonal Averaged One-Dependence Estimators: A Novel Algorithm to Address Seasonal Concept Drift in High-Dimensional Stream Classification

1 code implementation27 Jun 2020 Rakshitha Godahewa, Trevor Yann, Christoph Bergmeir, Francois Petitjean

This paper explores how to best handle seasonal drift in the specific context of news article categorization (or classification/tagging), where seasonal drift is overwhelmingly the main type of drift present in the data, and for which the data are high-dimensional.

Classification General Classification

Time Series Extrinsic Regression

1 code implementation23 Jun 2020 Chang Wei Tan, Christoph Bergmeir, Francois Petitjean, Geoffrey I. Webb

This paper studies Time Series Extrinsic Regression (TSER): a regression task of which the aim is to learn the relationship between a time series and a continuous scalar variable; a task closely related to time series classification (TSC), which aims to learn the relationship between a time series and a categorical class label.

regression Time Series +3

Monash University, UEA, UCR Time Series Extrinsic Regression Archive

2 code implementations19 Jun 2020 Chang Wei Tan, Christoph Bergmeir, Francois Petitjean, Geoffrey I. Webb

We refer to this problem as Time Series Extrinsic Regression (TSER), where we are interested in a more general methodology of predicting a single continuous value, from univariate or multivariate time series.

Benchmarking regression +4

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

Machine learning applications in time series hierarchical forecasting

no code implementations1 Dec 2019 Mahdi Abolghasemi, Rob J. Hyndman, Garth Tarr, Christoph Bergmeir

We perform an in-depth analysis of 61 groups of time series with different volatilities and show that ML models are competitive and outperform some well-established models in the literature.

BIG-bench Machine Learning Time Series +1

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

LoRMIkA: Local rule-based model interpretability with k-optimal associations

no code implementations11 Aug 2019 Dilini Rajapaksha, Christoph Bergmeir, Wray Buntine

In this paper, we propose Local Rule-based Model Interpretability with k-optimal Associations (LoRMIkA), a novel model-agnostic approach that obtains k-optimal association rules from a neighbourhood of the instance to be explained.

BIG-bench Machine Learning counterfactual +1

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.