Forecasting wholesale prices of yellow corn through the Gaussian process regression

Jin, Bingzi; Xu, Xiaojie

doi:10.1007/s00521-024-09531-2

Cited by 19 publications

(2 citation statements)

References 218 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As for performance evaluation, two representative types are widely used in related research, i.e., prediction accuracy and recommendation accuracy (Li et al, 2023). To estimate prediction accuracy, several metrics have been developed, such as RMSE (root mean square error), MAE (mean absolute error), and relative root mean square error (Jin & Xu, 2024a;Jin & Xu, 2024b). Among them, we select the first two metrics as they are commonly used for evaluating recommender systems.…”

Section: Performance Metricsmentioning

confidence: 99%

Time-Aware Similarity Integration for User-Based Collaborative Filtering

Lee

2024

JCCE

View full text Add to dashboard Cite

A time-aware collaborative filtering-based recommender system provides item recommendations for the current user by prioritizing recent items preferred by similar neighbors over past preferred items. The similarity measure critically affects the performance of the system, and this study focuses on measuring the similarity between users that changes over time. After dividing the users’ rating time into intervals and computing similarity for each time interval, the final similarity is generated as a weighted sum by assigning lower weights to past similarity values and higher weights to more recent similarity values. Additionally, to ensure continuity of similarity measurement, consecutive time intervals are set to overlap. As a result of experiments applying the proposed method to the existing similarity measures, significant performance improvement was achieved in terms of some of the major performance metrics. In particular, the degree of coverage improvement was the highest, and the performance improvement effect was higher when the overlap size between time intervals was large rather than when it was small.

show abstract

Section: Performance Metricsmentioning

confidence: 99%

Time-Aware Similarity Integration for User-Based Collaborative Filtering

Lee

2024

JCCE

View full text Add to dashboard Cite

show abstract

“…Given that commodity prices commonly display patterns of irregular volatility Zhang, 2023p, 2024e;Negri et al, 2021;Xu, 2017aXu, , 2020Bisht, 2019;Shiferaw, 2012;, influence market participants' decisions significantly (Warren-Vega et al, 2022;Xu and Thurman, 2015b;Moe et al, 2008;Xu, 2014c;Wang et al, 2022;, and ultimately effect resource allocations and overall economic prosperity (Jin and Xu, 2024b;Shahid et al, 2022;Xu, 2019a, c;Fan et al, 2022;, it may not be necessary to emphasize the relevance of price estimates for certain commodities.…”

Section: Introductionmentioning

confidence: 99%

Wholesale price forecasts of green grams using the neural network

Jin,

2024

AJEB

Self Cite

View full text Add to dashboard Cite

PurposeAgriculture commodity price forecasts have long been important for a variety of market players. The study we conducted aims to address this difficulty by examining the weekly wholesale price index of green grams in the Chinese market. The index covers a ten-year period, from January 1, 2010, to January 3, 2020, and has significant economic implications.Design/methodology/approachIn order to address the nonlinear patterns present in the price time series, we investigate the nonlinear auto-regressive neural network as the forecast model. This modeling technique is able to combine a variety of basic nonlinear functions to approximate more complex nonlinear characteristics. Specifically, we examine prediction performance that corresponds to several configurations across data splitting ratios, hidden neuron and delay counts, and model estimation approaches.FindingsOur model turns out to be rather simple and yields forecasts with good stability and accuracy. Relative root mean square errors throughout training, validation and testing are specifically 4.34, 4.71 and 3.98%, respectively. The results of benchmark research show that the neural network produces statistically considerably better performance when compared to other machine learning models and classic time-series econometric methods.Originality/valueUtilizing our findings as independent technical price forecasts would be one use. Alternatively, policy research and fresh insights into price patterns might be achieved by combining them with other (basic) prediction outputs.

show abstract

Forecasting sustainable development goals scores by 2030 using machine learning models

Chenary,

Pirian Kalat,

Sharifi

2024

Sustainable Development

View full text Add to dashboard Cite

The Sustainable Development Goals (SDGs) set by the United Nations are a worldwide appeal to eliminate poverty, preserve the environment, address climate change, and guarantee that everyone experiences peace and prosperity by 2030. These 17 goals cover various global issues concerning health, education, inequality, environmental decline, and climate change. Several investigations have been carried out to track advancements toward these goals. However, there is limited research on forecasting SDG scores. This research aims to forecast SDG scores for global regions by 2030 using ARIMAX and LR (Linear Regression) smoothed by HW (Holt‐Winters') multiplicative technique. To enhance model performance, we used predictors identified from the SDGs that are more likely to be influenced by Artificial Intelligence (AI) in the future. The forecast results for 2030 show that “OECD countries” (80) (with a 2.8% change) and “Eastern Europe and Central Asia” (74) (with a 2.37% change) are expected to achieve the highest SDG scores. “Latin America and the Caribbean” (73) (with a 4.17% change), “East and South Asia” (69) (with a 2.64% change), “Middle East and North Africa” (68) (with a 2.32% change), and “Sub‐Saharan Africa” (56) (with a 7.2% change) will display lower levels of SDG achievement, respectively.

show abstract

Forecasting wholesale prices of yellow corn through the Gaussian process regression

Cited by 19 publications

References 218 publications

Time-Aware Similarity Integration for User-Based Collaborative Filtering

Time-Aware Similarity Integration for User-Based Collaborative Filtering

Wholesale price forecasts of green grams using the neural network

Forecasting sustainable development goals scores by 2030 using machine learning models

Contact Info

Product

Resources

About