Journal Articles

Permanent URI for this collectionhttps://mro.massey.ac.nz/handle/10179/7915

Browse

Filters

2021 - 20246

Settings

Has files: YesSubject: search.filters.subject.forecasting

Search Results

Now showing 1 - 6 of 6
  • Thumbnail Image
    Item
    Can large language models help predict results from a complex behavioural science study?
    (The Royal Society, 2024-09) Lippert S; Dreber A; Johannesson M; Tierney W; Cyrus-Lai W; Uhlmann EL; Emotion Expression Collaboration; Pfeiffer T
    We tested whether large language models (LLMs) can help predict results from a complex behavioural science experiment. In study 1, we investigated the performance of the widely used LLMs GPT-3.5 and GPT-4 in forecasting the empirical findings of a large-scale experimental study of emotions, gender, and social perceptions. We found that GPT-4, but not GPT-3.5, matched the performance of a cohort of 119 human experts, with correlations of 0.89 (GPT-4), 0.07 (GPT-3.5) and 0.87 (human experts) between aggregated forecasts and realized effect sizes. In study 2, providing participants from a university subject pool the opportunity to query a GPT-4 powered chatbot significantly increased the accuracy of their forecasts. Results indicate promise for artificial intelligence (AI) to help anticipate-at scale and minimal cost-which claims about human behaviour will find empirical support and which ones will not. Our discussion focuses on avenues for human-AI collaboration in science.
  • Thumbnail Image
    Item
    Forecasting patient demand at urgent care clinics using explainable machine learning
    (John Wiley & Sons Ltd on behalf of The Institution of Engineering and Technology and Chongqing University of Technology., 2023-09-01) Susnjak T; Maddigan P
    Urgent care clinics and emergency departments around the world periodically suffer from extended wait times beyond patient expectations due to surges in patient flows. The delays arising from inadequate staffing levels during these periods have been linked with adverse clinical outcomes. Previous research into forecasting patient flows has mostly used statistical techniques. These studies have also predominately focussed on short-term forecasts, which have limited practicality for the resourcing of medical personnel. This study joins an emerging body of work which seeks to explore the potential of machine learning algorithms to generate accurate forecasts of patient presentations. Our research uses datasets covering 10 years from two large urgent care clinics to develop long-term patient flow forecasts up to one quarter ahead using a range of state-of-the-art algorithms. A distinctive feature of this study is the use of eXplainable Artificial Intelligence (XAI) tools like Shapely and LIME that enable an in-depth analysis of the behaviour of the models, which would otherwise be uninterpretable. These analysis tools enabled us to explore the ability of the models to adapt to the volatility in patient demand during the COVID-19 pandemic lockdowns and to identify the most impactful variables, resulting in valuable insights into their performance. The results showed that a novel combination of advanced univariate models like Prophet as well as gradient boosting, into an ensemble, delivered the most accurate and consistent solutions on average. This approach generated improvements in the range of 16%–30% over the existing in-house methods for estimating the daily patient flows 90 days ahead.
  • Thumbnail Image
    Item
    Short-Term Wind Speed Forecasting Based on Hybrid MODWT-ARIMA-Markov Model
    (IEEE, 2021-06-08) Yousuf MU; Al-Bahadly I; Avci E; Do TD
    Markov chains (MC) are statistical models used to predict very short to short-term wind speed accurately. Such models are generally trained with a single moving window. However, wind speed time series do not possess an equal length of behavior for all horizons. Therefore, a single moving window can provide reasonable estimates but is not an optimal choice. In this study, a forecasting model is proposed that integrates MCs with an adjusting dynamic moving window. The model selects the optimal size of the window based on a similar approach to the leave-one-out method. The traditional model is further optimized by introducing a self-adaptive state categorization algorithm. Instead of synthetically generating time series, the modified model directly predicts one-step ahead wind speed. Initial results indicate that adjusting the moving window MC prediction model improved the forecasting performance of a single moving window approach by 50%. Based on preliminary findings, a novel hybrid model is proposed integrating maximal overlap discrete wavelet transform (MODWT) with auto-regressive integrated moving average (ARIMA) and adjusting moving window MC. It is evident from the literature that MC models are suitable for predicting residual sequences. However, MCs were not considered as a primary forecasting model for the decomposition-based hybrid approach in any wind forecasting studies. The improvement of the novel model is, on average, 55% for single deep learning models and 30% for decomposition-based hybrid models.
  • Thumbnail Image
    Item
    Wind speed prediction for small sample dataset using hybrid first-order accumulated generating operation-based double exponential smoothing model
    (John Wiley & Sons, Inc, 2022-03-09) Yousuf MU; Al-Bahadly I; Avci E
    Wind power generation has recently emerged in many countries. Therefore, the availability of long-term historical wind speed data at various potential wind farm sites is limited. In these situations, such forecasting models are needed that comprehensively address the uncertainty of raw data based on small sample size. In this study, a hybrid first-order accumulated generating operation-based double exponential smoothing (AGO-HDES) model is proposed for very short-term wind speed forecasts. Firstly, the problems of traditional Holt's double exponential smoothing model are highlighted considering the wind speed data of Palmerston North, New Zealand. Next, three improvements are suggested for the traditional model with a rolling window of six data points. A mixed initialization method is introduced to improve the model performance. Finally, the superiority of the novel model is discussed by comparing the accuracy of the AGO-HDES model with other forecasting models. Results show that the AGO-HDES model increased the performance of the traditional model by 10%. Also, the modified model performed 7% better than other considered models with three times faster computational time.
  • Thumbnail Image
    Item
    Present and future distribution of bat hosts of sarbecoviruses: implications for conservation and public health
    (The Royal Society, 2022-05-25) Muylaert RL; Kingston T; Luo J; Vancine MH; Galli N; Carlson CJ; John RS; Rulli MC; Hayman DTS
    Global changes in response to human encroachment into natural habitats and carbon emissions are driving the biodiversity extinction crisis and increasing disease emergence risk. Host distributions are one critical component to identify areas at risk of viral spillover, and bats act as reservoirs of diverse viruses. We developed a reproducible ecological niche modelling pipeline for bat hosts of SARS-like viruses (subgenus Sarbecovirus), given that several closely related viruses have been discovered and sarbecovirus-host interactions have gained attention since SARS-CoV-2 emergence. We assessed sampling biases and modelled current distributions of bats based on climate and landscape relationships and project future scenarios for host hotspots. The most important predictors of species distributions were temperature seasonality and cave availability. We identified concentrated host hotspots in Myanmar and projected range contractions for most species by 2100. Our projections indicate hotspots will shift east in Southeast Asia in locations greater than 2°C hotter in a fossil-fuelled development future. Hotspot shifts have implications for conservation and public health, as loss of population connectivity can lead to local extinctions, and remaining hotspots may concentrate near human populations.
  • Thumbnail Image
    Item
    Forecasting the publication and citation outcomes of COVID-19 preprints
    (The Royal Society, 2022-09) Gordon M; Bishop M; Chen Y; Dreber A; Goldfedder B; Holzmeister F; Johannesson M; Liu Y; Tran L; Twardy C; Wang J; Pfeiffer T
    Many publications on COVID-19 were released on preprint servers such as medRxiv and bioRxiv. It is unknown how reliable these preprints are, and which ones will eventually be published in scientific journals. In this study, we use crowdsourced human forecasts to predict publication outcomes and future citation counts for a sample of 400 preprints with high Altmetric score. Most of these preprints were published within 1 year of upload on a preprint server (70%), with a considerable fraction (45%) appearing in a high-impact journal with a journal impact factor of at least 10. On average, the preprints received 162 citations within the first year. We found that forecasters can predict if preprints will be published after 1 year and if the publishing journal has high impact. Forecasts are also informative with respect to Google Scholar citations within 1 year of upload on a preprint server. For both types of assessment, we found statistically significant positive correlations between forecasts and observed outcomes. While the forecasts can help to provide a preliminary assessment of preprints at a faster pace than traditional peer-review, it remains to be investigated if such an assessment is suited to identify methodological problems in preprints.