AI Article Synopsis

  • Short-cycle agricultural product sales forecasting helps reduce food waste by predicting demand accurately, matching supply with consumer needs.
  • A hierarchical prediction model combining Random Forest (RF) and Extreme Gradient Boosting (XGBoost) is introduced to handle data volatility and improve prediction accuracy.
  • Results show this model outperforms standalone RF and XGBoost, reducing prediction errors significantly and demonstrating effectiveness across various agricultural products, thereby optimizing supply chains and minimizing food waste.

Article Abstract

Short-cycle agricultural product sales forecasting significantly reduces food waste by accurately predicting demand, ensuring producers match supply with consumer needs. However, the forecasting is often subject to uncertain factors, resulting in highly volatile and discontinuous data. To address this, a hierarchical prediction model that combines RF-XGBoost is proposed in this work. It adopts the Random Forest (RF) in the first layer to extract residuals and achieve initial prediction results based on correlation features from Grey Relation Analysis (GRA). Then, a new feature set based on residual clustering features is generated after the hierarchical clustering is applied to classify the characteristics of the residuals. Subsequently, Extreme Gradient Boosting (XGBoost) acts as the second layer that utilizes those residual clustering features to yield the prediction results. The final prediction is by incorporating the results from the first layer and second layer correspondingly. As for the performance evaluation, using agricultural product sales data from a supermarket in China from 1 July 2020 to 30 June 2023, the results demonstrate superiority over standalone RF and XGBoost, with a Mean Absolute Percentage Error (MAPE) reduction of 10% and 12%, respectively, and a coefficient of determination (R) increase of 22% and 24%, respectively. Additionally, its generalization is validated across 42 types of agricultural products from six vegetable categories, showing its extensive practical ability. Such performances reveal that the proposed model beneficially enhances the precision of short-term agricultural product sales forecasting, with the advantages of optimizing the supply chain from producers to consumers and minimizing food waste accordingly.

Download full-text PDF

Source
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC11431005PMC
http://dx.doi.org/10.3390/foods13182936DOI Listing

Publication Analysis

Top Keywords

agricultural product
16
product sales
16
sales forecasting
12
short-cycle agricultural
8
food waste
8
residual clustering
8
clustering features
8
second layer
8
agricultural
5
hierarchical rf-xgboost
4

Similar Publications

A Sorghum / Homolog Functions in PAMP-Triggered Immunity and Cell Death in Response to Infection.

Phytopathology

January 2025

University of Florida, Microbiology & Cell Science, Cancer/Genetics Research Complex 302, 2033 Mowry Road, Gainesville, Florida, United States, 32610;

(L.) Moench is the fifth most important cereal crop and expected to gain prominence due to its versatility, low input requirements, and tolerance to hot and dry conditions. In warm and humid environments the productivity of sorghum is severely limited by the hemibiotrophic fungal pathogen , the causal agent of anthracnose.

View Article and Find Full Text PDF

The Dromedary camel has a remarkable history amongst cultures across Asia and northern Africa, serving multiple purposes ranging from providing milk, textiles, racing, and acting as pack animals. Recent genetic studies have revealed that many dromedaries are genetically homogenous, indicating that they do not represent different breeds, advocating for camel 'type' over camel 'breed'. In this study, we leveraged whole genome sequencing (WGS) to sequence 15 Jordanian Alia camels for the first time, alongside 9 Jordanian mixed camels from diverse locations within the country.

View Article and Find Full Text PDF

In this study, residue depletion and withdrawal time estimation of tilmicosin were examined in Taihe black-bone silky fowls (TBSFs) after oral administration for three consecutive days at a dose of 75 mg/L in water. The tilmicosin concentrations in liver, kidney, muscle, and skin/fat of TBSFs collected from different time points (0.16, 1, 3, 5, 7, 9, 12, 20, 30, 40 days after last administration) were determined by UPLC-MS/MS.

View Article and Find Full Text PDF

Addressing global food security demands urgent improvement in agricultural productivity, particularly in developing economies where market imperfections are perverse and resource constraints prevail. While microcredit is widely acknowledged as a tool for economic empowerment, its role in facilitating agricultural technology adoption and improving agricultural incomes remains underexplored. This study examines the synergistic effects of microcredit access and agricultural technology adoption on the incomes of maize farmers in Kenya.

View Article and Find Full Text PDF

U-Type-Shaped Curves Across Economics, Biology, and Infection.

Surg Infect (Larchmt)

January 2025

Division of Biological Sciences, University of Chicago, Chicago, Illinois, USA.

Major threats to the economic future of several nations include climate change, infectious pandemics, and drug-resistant bacteria. The rise and fall of each of these behaviors seems to conform to a U-shaped or inverted U-shaped curve. In academic medicine, stakeholders in the field (infection control personnel, epidemiologists, and vaccinologists) will argue that infectious outbreaks can be prevented by surveillance programs and the development of new drugs (antibiotics, vaccines, etc.

View Article and Find Full Text PDF

Want AI Summaries of new PubMed Abstracts delivered to your In-box?

Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!