Short-term forecasting of vegetable prices based on LSTM model-Evidence from Beijing's vegetable data.

The vegetable sector is a vital pillar of society and an indispensable part of the national economic structure. As a significant segment of the agricultural market, accurately forecasting vegetable prices holds significant importance. Vegetable market pricing is subject to a myriad of complex influences, resulting in nonlinear patterns that conventional time series methodologies often struggle to decode. In this paper, we exploit the average daily price data of six distinct types of vegetables sourced from seven key wholesale markets in Beijing, spanning from 2009 to 2023. Upon training an LSTM model, we discovered that it exhibited exceptional performance on the test dataset. Demonstrating robust predictive performance across various vegetable categories, the LSTM model shows commendable generalization abilities. Moreover, LSTM model has a higher accuracy compared to several machine learning methods, including CNN-based time series forecasting approaches. With R2 score of 0.958 and MAE of 0.143, our LSTM model registers an enhancement of over 5% in forecast accuracy relative to conventional machine learning counterparts. Therefore, by predicting vegetable prices for the upcoming week, we envision this LSTM model application in real-world settings to aid growers, consumers, and policymakers in facilitating informed decision-making. The insights derived from this forecasting research could augment market transparency and optimize supply chain management. Furthermore, it contributes to the market stability and the balance of supply and demand, offering a valuable reference for the sustainable development of the vegetable industry.

Turning the tide on big cat trade: Expert opinion on trends and conservation lessons from the Republic of Korea.

Unsustainable trade in big cats affects all species in the genus, Panthera, and is one of the foremost threats to their conservation. To provide further insight into the impact of policy interventions intended to address this issue, we examine the case study of the Republic of Korea (South Korea), which in the early 1990s was one of the world's largest importers of tiger (Panthera tigris) bone and a major manufacturer of tiger-derived medicinal products. In 1993, South Korea became a Party to the Convention on International Trade in Endangered Species (CITES) and introduced a ban on commercial trade in CITES Appendix I-listed big cats a year later. We used an expert-based questionnaire survey and an exploration of the CITES trade database to investigate what has since happened to big cat trade in South Korea. Expert opinion suggested that big cat trade has likely substantially reduced since the early 1990s, as a result of the trade ban and broad socioeconomic changes. However, illegal trade has not been eradicated entirely and we were able to confirm that products reportedly derived from big cats were still publicly available for sale on a range of Korean online marketplaces, sometimes openly. The items most commonly reported by respondents from post-1994 trade and supported by expert-led evidence were tiger and leopard (Panthera pardus) skins and tiger bone wine. Although South Korea may provide a useful case study of a historically significant consumer country for tiger which has made strong progress in addressing unsustainable levels of big cat trade within a short period of time, there remains a need to address recalcitrant small-scale, illegal trade. We also recommend further investigation regarding reports of South Korean nationals being involved in illegal trade in tiger-derived products in Southeast Asia.

Heteroscedasticity effects as component to future stock market predictions using RNN-based models.

Heteroscedasticity effects are useful for forecasting future stock return volatility. Stock volatility forecasting provides business insight into the stock market, making it valuable information for investors and traders. Predicting stock volatility is a crucial task and challenging. This study proposes a hybrid model that predicts future stock volatility values by considering the heteroscedasticity element of the stock price. The proposed model is a combination of Generalized Autoregressive Conditional Heteroskedasticity (GARCH) and a well-known Recurrent Neural Network (RNN) algorithm Long Short-Term Memory (LSTM). This proposed model is referred to as GARCH-LSTM model. The proposed model is expected to improve prediction accuracy by considering heteroscedasticity elements. First, the GARCH model is employed to estimate the model parameters. After that, the ARCH effect test is used to test the residuals obtained from the model. Any untrained heteroscedasticity element must be found using this step. The hypothesis of the ARCH test yielded a p-value less than 0.05 indicating there is valuable information remaining in the residual, known as heteroscedasticity element. Next, the dataset with heteroscedasticity is then modelled using an LSTM-based RNN algorithm. Experimental results revealed that hybrid GARCH-LSTM had the lowest MAE (7.961), RMSE (10.466), MAPE (0.516) and HMAE (0.005) values compared with a single LSTM. The accuracy of forecasting was also significantly improved by 15% and 13% with hybrid GARCH-LSTM in comparison to single LSTMs. Furthermore, the results reveal that hybrid GARCH-LSTM fully exploits the heteroscedasticity element, which is not captured by the GARCH model estimation, outperforming GARCH models on their own. This finding from this study confirmed that hybrid GARCH-LSTM models are effective forecasting tools for predicting stock price movements. In addition, the proposed model can assist investors in making informed decisions regarding stock prices since it is capable of closely predicting and imitating the observed pattern and trend of KLSE stock prices.

Food price trends during the COVID-19 pandemic in Brazil.

The present study aims to analyze the trends in food price in Brazil with emphasis on the period of the Covid-19 pandemic (from March 2020 to March 2022). Data from the Brazilian Household Budget Survey and the National System of Consumer Price Indexes were used as input to create a novel data set containing monthly prices (R$/Kg) for the foods and beverages most consumed in the country between January 2018 and March 2022. All food items were divided according to the Nova food classification system. We estimated the mean price of each food group for each year of study and the entire period. The monthly price of each group was plotted to analyze changes from January 2018 to March 2022. Fractional polynomial models were used to synthesize price changes up to 2025. Results of the present study showed that in Brazil unprocessed or minimally processed foods and processed culinary ingredients were more affordable than processed and ultra-processed foods. However, trend analyses suggested the reversal of the pricing pattern. The anticipated changes in the prices of minimally processed food relative to ultra-processed food, initially forecasted for Brazil, seem to reflect the impact of the Covid-19 pandemic on the global economy. These results are concerning as the increase in the price of healthy foods aggravates food and nutrition insecurity in Brazil. Additionally, this trend encourages the replacement of traditional meals for the consumption of unhealthy foods, increasing a health risk to the population.

Causality-driven multivariate stock movement forecasting.

Our study aims to investigate the interdependence between international stock markets and sentiments from financial news in stock forecasting. We adopt the Temporal Fusion Transformers (TFT) to incorporate intra and inter-market correlations and the interaction between the information flow, i.e. causality, of financial news sentiment and the dynamics of the stock market. The current study distinguishes itself from existing research by adopting Dynamic Transfer Entropy (DTE) to establish an accurate information flow propagation between stock and sentiments. DTE has the advantage of providing time series that mine information flow propagation paths between certain parts of the time series, highlighting marginal events such as spikes or sudden jumps, which are crucial in financial time series. The proposed methodological approach involves the following elements: a FinBERT-based textual analysis of financial news articles to extract sentiment time series, the use of the Transfer Entropy and corresponding heat maps to analyze the net information flows, the calculation of the DTE time series, which are considered as co-occurring covariates of stock Price, and TFT-based stock forecasting. The Dow Jones Industrial Average index of 13 countries, along with daily financial news data obtained through the New York Times API, are used to demonstrate the validity and superiority of the proposed DTE-based causality method along with TFT for accurate stock Price and Return forecasting compared to state-of-the-art time series forecasting methods.

Smoking out Australia's growing illicit tobacco market: Current trends and future challenges.

Data from the Australian Taxation Office and Australian Border Force show notable recent increases in illicit tobacco seizures across Australia. The illicit tobacco market results in substantial losses in tax revenue, funds organised crime, and perpetuates tobacco use, threatening to undermine Australia's ability to achieve its national commercial tobacco endgame goal of 5 % or less smoking prevalence by 2030. This commentary discusses recent trends in Australia's illicit tobacco trade, reasons why this is of concern, potential drivers of Australians' illicit tobacco use, and policy measures that could be implemented to mitigate increasing illicit tobacco trade such as implementing a track and trace system, increased investment in the Australian Border Force to enhance detection of illicit tobacco shipments at Australia's borders, and encouraging public tip-offs of illicit tobacco sales.

Beyond the smoke: Historical analysis of the revenue implications of state cigarette tax policies, 1989 to 2019.

INTRODUCTION: While cigarette taxes are a vital tobacco control tool, their impact on cigarette tax revenue has been largely understudied in the extant literature. This study examines how the level of cigarette taxes affects the revenue generated from cigarettes in the United States over a thirty-year period. METHODS: We obtained the Tax Burden Data from the Centers for Disease Control and Prevention (1989-2019). Our dependent variables were gross cigarette tax revenue and per capita gross cigarette tax revenue, and our independent variable was state tax per pack. We used two-way fixed effects to estimate the relationship between state cigarette tax revenue and cigarette taxes, adjusting for state-level sociodemographic characteristics, state-fixed effects, and time trends. RESULTS: The study reveals that raising cigarette state tax by 10 % led to a 7.2 % to 7.5 % increase in cigarette tax revenue. We also found state and regional variation in taxes and revenue, with the Northeast region having the highest taxes per pack and tax revenues. In 2019, most states had low or moderate taxes per pack and tax revenues per capita, while a few states had high taxes per pack and tax revenues per capita. CONCLUSIONS: Our research demonstrates the positive impact of increased cigarette taxes on state tax revenue over three decades. Not only do higher taxes aid in tobacco control, but they also enhance state revenues that can be reinvested in state initiatives. Some states could potentially optimize their tax rates.

Trends in purchasing cross-border, illicit and home-brewed alcohol: A population study in Great Britain, 2020-2023.

INTRODUCTION: The last 3 years have seen substantial changes in Great Britain (GB) including the COVID-19 pandemic, cost-of-living crisis and policy changes such as minimum unit pricing. We examined changes in purchasing cross-border, illicit and home-brewed alcohol among risky drinkers over this period. METHODS: Data were used from 22,086 adult (≥18 years) increasing/higher-risk drinkers (AUDIT-C ≥5) participating in a monthly cross-sectional survey between October 2020 and August 2023. We estimated time trends in the proportion reporting obtaining alcohol from: (i) cross-border (any/within-GB/international); (ii) illicit; and (iii) home-brewed sources in the past 6 months. RESULTS: Between October 2020 and August 2023, the proportion reporting cross-border alcohol purchases increased (from 8.5% to 12.5% overall; prevalence ratio [PR] = 1.47 [95% CI 1.17-1.86]). This was largely driven by an increase in cross-border purchases abroad (PR = 1.52 [1.13-2.05]), with a smaller, uncertain increase in cross-border purchases within GB (PR = 1.37 [0.96-1.95]). The prevalence of cross-border alcohol purchasing was higher in Wales (13.8% [12.3-15.4%]) and Scotland (6.1% [5.4-6.8%]) than England (3.6% [3.3-3.9%]). There was little change in illicit alcohol purchasing in England or Wales (4.1% [3.7-4.4%]; 4.2% [3.2-5.1%]), but in Scotland it fell from 5.7% to 2.4% (PR = 0.42 [0.19-0.81]). Home-brewed alcohol was rare (GB: 3.1% [2.9-3.4]) and stable. DISCUSSION AND CONCLUSIONS: The proportion of increasing/higher-risk drinkers in GB purchasing cross-border alcohol increased between October 2020 and August 2023, due to an increase in people buying alcohol abroad. Cross-border alcohol purchases within GB were more commonly reported in Wales and Scotland. The small proportion purchasing illicit alcohol did not change substantially in England or Wales, but fell by half in Scotland.

Trends in Phenylephrine and Pseudoephedrine Sales in the US.

This study examines purchasing patterns regarding oral decongestants, concerns about their efficacy, and the need for timelier postmarket evaluation.

Canada's Alcohol Deficit, 2007-2020: Social Cost, Public Revenue, Magnitudes of Alcohol Use, and the Per-Drink Net Deficit for a Fourteen-Year Period.

OBJECTIVE: Governments generate substantial revenue from the distribution and sale of alcoholic beverages. However, the use of this alcohol results in considerable public costs for health care, criminal justice, and economic loss of production. Because comparisons of these two sides of the same coin are limited, this study aims to estimate this net alcohol surplus or deficit in Canada and each province/territory for a 14-year study period. METHOD: Net government revenue from alcohol sales and net social costs of alcohol use were estimated for Canada and each province/territory for all years of study from 2007 to 2020, and all dollar figures were Consumer Price Index-adjusted to 2020 Canadian dollars (CAD). The net alcohol surplus/deficit was estimated as the difference. Per capita recorded alcohol sold was from administrative sources and used as proxy to calculate alcohol used by adding an estimate of unrecorded use and converting to Canadian standard drinks (CSDs). The per-drink net deficit was the net deficit divided by CSDs. RESULTS: In Canada in 2020, governments generated CAD $13.3 billion in revenue from alcohol sales, but this was offset by $19.7 billion in social costs attributable to alcohol use. This "alcohol deficit" increased by 122.0% in real-dollar terms over the study period and reached a high of $6.4 billion in 2020. In 2020, the magnitude of the alcohol used in Canada was 16.8 billion CSDs. Each of these drinks resulted in a public net deficit of $0.379. CONCLUSIONS: Both alcohol use and the resulting public alcohol deficit are high in Canada. To mitigate these losses to the well-being of Canadians and their economy, government planners, regulators, and policymakers must urgently deploy evidence-based alcohol policies toward reducing the magnitude of alcohol used in Canada.

Hybrid deep learning models with multi-classification investor sentiment to forecast the prices of China's leading stocks.

The prediction of stock prices has long been a captivating subject in academic research. This study aims to forecast the prices of prominent stocks in five key industries of the Chinese A-share market by leveraging the synergistic power of deep learning techniques and investor sentiment analysis. To achieve this, a sentiment multi-classification dataset is for the first time constructed for China's stock market, based on four types of sentiments in modern psychology. The significant heterogeneity of sentiment changes in the sectors' leading stock markets is trained and mined using the Bi-LSTM-ATT model. The impact of multi-classification investor sentiment on stock price prediction was analyzed using the CNN-Bi-LSTM-ATT model. It finds that integrating sentiment indicators into the prediction of industry leading stock prices can enhance the accuracy of the model. Drawing upon four fundamental sentiment types derived from modern psychology, our dataset provides a comprehensive framework for analyzing investor sentiment and its impact on forecasting the stock prices of China's A-share market.

The roles of liquidity and delay in financial markets based on an optimal forecasting model.

We investigate the roles of liquidity and delay in financial markets through our proposed optimal forecasting model. The efficiency and liquidity of the financial market are examined using stochastic models that incorporate information delay. Based on machine learning, we estimate the in-sample and out-of-sample forecasting price performances of the six proposed methods using the likelihood function and Bayesian methods, and the out-of-sample prediction performance is compared with the benchmark model ARIMA-GARCH. We discover that the forecasting price performance of the proposed simplified delay stochastic model is superior to that of the benchmark methods by the test methods of a variety of loss function, superior predictive ability test (SPA), Akaike information criterion (AIC), and Bayesian information criterion (BIC). Using data from the Chinese stock market, the best forecasting model assesses the efficiency and liquidity of the financial market while accounting for information delay and trade probability. The rise in trade probability and delay time affects the stability of the return distribution and raises the risk, according to stochastic simulation. The empirical findings show that empirical and best forecasting approaches are compatible, that company size and liquidity (delay time) have an inverse relationship, and that delay time and liquidity have a nonlinear relationship. The most efficient have optimal liquidity.

Five-Year Sales for Newly Marketed Prescription Drugs With and Without Initial Orphan Drug Act Designation.

This study evaluates sales revenue earned in the first 5 years for newly marketed brand-name drugs with and without an initial orphan drug designation.

Us vehicles sales. Evidence of persistence after COVID-19.

In this paper, the sales of vehicles in the US are examined to understand if the shock caused by the current COVID-19 pandemic has had permanent or transitory effects on its subsequent evolution. Using monthly data from January 1976 until April 2021 and fractional integration methods, our results indicate that the series reverts and the shocks tend to disappear in the long run, even when they appear to be long lived. The results also indicate that the COVID-19 pandemic has not increased the degree of persistence of the series but, unexpectedly, has slightly reduced its dependence. Thus, shocks are transitory, long lived but, as time goes by, the recovery seems to be faster, which is possibly a sign of the strength of the industry.

Impacts of the COVID-19 pandemic on food prices: Evidence from storable and perishable commodities in India.

The supply chain disruptions caused by the COVID-19 outbreak have led to changes in food prices globally. The impact of COVID-19 on the price of essential and perishable food items in developing and emerging economies has been lacking. Using a recent phone survey by the World Bank, this study examines the impact of the COVID-19 pandemic on the prices of the three essential food items in India. The results indicate that price of basic food items such as atta (wheat flour) and rice increased significantly during the pandemic compared to the pre-pandemic period. In contrast, during the same period, the price of onions declined significantly. The findings may suggest panic-buying, hoarding, and storability of food items. The results further reveal that remittance income and cash transfers from the government negatively affected commodity prices. Thus, this study's findings suggest that families may have shifted the demand away from essential foods during the pandemic.