Supermarket Food Research Articles

Forecasting superstore fruit and vegetable sales based on ARIMA-LSTM

In the context of a fresh food supermarket, managing perishable vegetables, which have a notably limited shelf life, maintaining optimal stock levels becomes imperative for safeguarding profitability. This research paper intricately explores the analysis of numerous datasets using Power Query and Power BI, with a pivotal focus on devising a succinct coding system. To ensure data quality, outliers are meticulously eliminated using advanced techniques like linear interpolation and Z-Score processing. The ARIMA time series model is employed to predict the sales volume for each category in July, having been trained on data from June 2022 to June 2023, adeptly capturing historical sales patterns and emerging trends. Additionally, a parameter-tuned LSTM recurrent neural network, optimized with Adam's algorithm, is utilized to refine predictions, considering its inherent memory capabilities. A thoughtfully designed weighted average approach combines outputs from both models, strategically minimizing overfitting and enhancing prediction accuracy. The resultant research fortifies inventory management optimization, bolstering the supermarket's profitability while effectively meeting customer demands.

P865 Screening for low-processed breads - compositional analysis of food additives used in commercially available breads

Abstract Background Ultra-processed food (UPF) intake has been associated with the development of inflammatory bowel diseases (IBD), particularly Crohn’s disease (CD). Of UPF subgroups, commercially available breads showed greater risk, possibly due to the increasing presence of food additives (FA) like emulsifiers. As bread is a staple food worldwide, often consumed daily, we aimed to screen the ingredients and FA used in bread industry and to assess the availability of low processed breads. Methods We consecutively screened breads available at supermarket and health food store chains popular and widely distributed in Israel. Breads, pita breads and buns (excluding products without food labels), were analyzed by dietitians and categorized into one of three categories according to their processing level and FA types. Low processed category included ingredients used in traditional, home-made breads; medium processed category included FA like malt and added fibers; high processed category included FA like emulsifiers and preservatives, previously associated with impact on microbiota composition or implications on IBD. Results A total of 233 breads were screened, 160 are available at the supermarket, 56 at the health food store, and 17 in both. We categorized 195 (84%) as highly processed, 9 (4%) as medium processed and 29 (12%) as low processed. We identified 36 different types of FA and ingredients used. Most breads contained emulsifiers- 178 (76%) and –preservatives-189 (81%). The most used emulsifier was sodium stearoyl-2-lactylate (SSL, E-481), present in 86 breads (37%), followed by mono- and diglycerides of fatty acids (E-471), DATEM (E-472e) and carboxymethyl cellulose (CMC, E-466), found in 22%, 16% and 2% of breads, respectively. Interestingly, the emulsifier E-481, previously shown to induce microbial alterations, was found in 86 breads (52%) sold in the supermarket compared to none of the breads available in the health food store. Out of the 5 common preservatives, most of the breads contained calcium propionate (E-282) found in 112 (48%) and potassium sorbate (E-202) found in 42 (18%). Additives like enzymes were present in 159 (68%), gluten was added to 148 (64%) and 88 (38%) breads had added fibers. A greater portion of the breads contained yeast (85%) compared to sourdough (47%), with 30 (13%) containing only sourdough. Conclusion Most of the commercially available breads in Israel are highly processed. The use of emulsifiers, preservatives, added gluten and fibers is very common, yet low processed breads are available. These may be more recommended to patients with IBD. Further understanding of the role of FA in IBD etiology may potentially guide dietary recommendations for specific food choices.

Prediction Of Vegetable Pricing and Replenishment Based on ARIMA Model

Vegetables are indispensable consumer goods in the daily diet of the majority of consumers. Reasonable pricing and replenishment strategies of vegetables are conducive to maintaining the interests of agricultural producers and promoting the stable development of the market. The main contents of this paper are two points: one is to visualize the pre-processed data and establish the distribution map of vegetable sales in recent years; Secondly, the ARIMA time series prediction model was established by linear fitting of the data, and the feasibility test of the prediction results was carried out to obtain the total daily replenishment quantity and price of each vegetable category in a period of time. Under the background of the new era with low-carbon green as the mainstream, this research has broad development space and prospect. The pricing and replenishment strategies formulated in this study can reduce the waste of vegetables in the whole consumption supply chain, maintain the purchasing power and living standard of consumers, and meet the market demand. Marketing techniques that promote healthy foods in supermarkets are important to encourage healthy eating at the population level. The content of this study can provide ideas for the optimization of vegetable supply chain, further use of new technology, reduce waste, improve efficiency, and ensure the quality and supply stability of vegetables. This study is also helpful to analyze consumer behavior and understand consumers' reactions to vegetable price fluctuations and changes in purchasing behavior in order to better predict market trends and adjust production and supply strategies.

Optimization Of Automatic Pricing and Replenishment Decision Based on Time Series and BP Neural Network Model

In major fresh food supermarkets, vegetable products often have a short shelf life and poor product quality, which affects their sales. Therefore, it is particularly important to make replenishment decisions for each vegetable category on the same day without knowing the specific individual product and purchase price. This article focuses on the problem of automatic pricing and replenishment decision-making for vegetable products. Based on the fact that vegetable products have a relatively short shelf life, the automatic pricing and replenishment strategies for vegetable products are optimized, indirectly proving the correlation between certain individual products. A mathematical model is constructed using time series and BP neural network models to obtain corresponding replenishment strategies, Finally, provide recommendations on automatic pricing and replenishment decisions for vegetable products. The "cost plus pricing" method involved in this question plays a crucial role in the pricing of vegetables. At the same time, from the perspectives of the demand side and supply side, the limitations of sales time and sales space are also particularly important.

Research On Time Series Forecasting-Based Pricing Strategy for Supermarket

In fresh food supermarkets, vegetables have a short shelf life. It is of great practical significance to price different products based on market research in order to maximize the benefits of supermarkets. The aim of this paper is to investigate and address the pricing decision question of vegetable products in fresh food supermarkets. This article investigates the correlation between cost-based pricing and sales revenue by establishing linear regression models and time series models.In addition, we have also made price predictions for various categories of products in the supermarket. Finally, this article provides pricing decisions for various categories in the first week of July 2023 for the supermarket.

Pricing And Replenishment Strategies for Vegetable Products Based on Planning Models

Reasonable pricing and replenishment strategies for vegetable products are crucial for maximizing profits for fresh food supermarkets. This article mainly studies the relationship between the sales volume and sales unit price of vegetable products and time, establishes a pricing and replenishment decision model based on BP neural network and mathematical programming, and provides strategies to meet the requirements of maximizing the interests of supermarkets.

Research On Vegetable Replenishment and Pricing Based on LSTM Neural Network Prediction Modeling

Vegetables in fresh food supermarkets face challenges with pricing and replenishment since the majority of vegetable varieties have a short shelf life. Fresh food supermarkets must replenish goods based on sales history and demand. In this paper, the pricing and replenishment decisions of fresh supermarkets are predicted using the random forest and LSTM neural network prediction models. The findings indicate that the prediction model in this paper can have a good predictive effect and that the decisions made by fresh supermarkets regarding pricing and replenishment are related to the historical time series data. This paper's study can assist in resolving price and replenishment issues in fresh food stores, which will have some positive economic effects.

Places to purchase food in urban and rural areas of Brazil.

To describe the locations of food and beverage acquisition in Brazil, according to the level of food processing and household location (urban/rural). Data from 49,489 households from the Household Budget Survey 2017-2018 were used. Information regarding food and beverages was collected through a collective acquisition booklet over 7 consecutive days. Locations were classified into 10 groups on the basis of similarities in sales structure and mode of food offering, and food and beverages were categorized according to the NOVA classification. The frequency of households acquiring food in each location was estimated, as well as the acquisition frequency according to processing level, considering significance through non-overlapping 95% confidence intervals. Half of the households (51.9%) acquired food in supermarkets, contributing to both the acquisition of fresh and minimally processed foods (92.2% in urban; 90.2% in rural) and ultra-processed foods (78.6% in urban; 74.1% in rural). For the urban area, the Supermarket (55.0%), Bakery (46.5%) and Small markets (43.1%) are among the places with the highest frequency of food acquisition, while for rural areas, it is found that Small Markets (53%), Supermarkets (32.3%) and Home production (31.0%) presented the highest frequencies. The acquisition of food and beverages for household consumption in Brazil differs according to household location (urban/rural), indicating the importance of the community food environment in the consumption patterns of ultra-processed foods.

An unintended consequence of COVID-19 immunity passports-quasi-experimental evidence of moral hazard observed after implementing the domestic Green Pass policy during the second wave of the COVID-19 pandemic in Italy.

Amidst the second wave of the COVID-19 pandemic, Italian policymakers mandated to exhibit evidence of vaccination or immunity (the Green Pass) as a condition to access retail premises and public offices. This study aims to offer evidence, in a quasi-experimental setting, suggesting that an unintended consequence of this policy was the emergence of moral hazard. Google visit duration data measured the time customers typically spend on retail premises or public offices. A pairwise comparison of median visit time per premise was performed at a six-week interval before and after the introduction of the Green Pass. This study is the first to provide evidence of "ex-post" moral hazard associated with introducing a domestic Green Pass policy. The median visiting time on premises that required digital immunity control significantly increased after introducing the domestic Green Pass policy, contrary to other public premises where access remained free of limitations. The increase in median visit time in premises with faster customer turnaround, such as coffee shops (+49%) and fast-food restaurants (+45%), was lower than the increase observed for fine-dining restaurants (+74%) and pizzerias (+163%). No significant increase in median visit time was observed in premises where the Green Pass was not required, such as food supermarkets, retail non-food shops, post offices, banks, pharmacies, and gas stations. The evidence of moral hazard highlights the critical issue of unintended consequences stemming from public health policies. This discovery is pivotal for policymakers, indicating that unforeseen behavioral adjustments could offset the intended benefits despite the intent to reduce risk through measures like the Green Pass.

The development of sodium reduction targets for New Zealand fast foods and a comparison with the current sodium contents of products.

Sodium intake attributed to fast food is increasing globally. This research aims to develop maximum sodium reduction targets for New Zealand (NZ) fast foods and compare them with the current sodium content of products. Sodium content and serving size data were sourced from an existing database of major NZ fast-food chains. Target development followed a step-by-step process, informed by international targets and serving sizes, and previous methods for packaged supermarket foods. Sodium reduction targets were set per 100 g and serving, using a 40% reduction in the mean sodium content or the value met by 35-45% of products. Thirty-four per cent (1797/5246) of products in the database had sodium data available for target development. Sodium reduction targets were developed for 17 fast-food categories. Per 100 g targets ranged from 158 mg for 'Other salads' to 665 mg for 'Mayonnaise and dressings'. Per serving targets ranged from 118 mg for 'Sauce' to 1270 mg for 'Burgers with cured meat'. The largest difference between the current mean sodium content and corresponding target was for 'Other salads' and 'Grilled Chicken' (both -40% per 100g) and 'Fries and potato products' (-45% per serving), and the smallest, 'Pizza with cured meat toppings' (-3% per 100 g) and 'Pies, tarts, sausage rolls and quiches' (-4% per serving). The results indicate the display of nutrition information should be mandated and there is considerable room for sodium reduction in NZ fast foods. The methods described provide a model for other countries to develop country-specific, fast-food sodium reduction targets.

The Research on Pricing and Replenishment Optimization of Fresh Supermarket Vegetable Products based on Sales Data

This study delves into the challenges and complexities of vegetable sales management in modern commercial environments, particularly in fresh food supermarkets. By utilizing descriptive statistics and visual analysis of sales data, the study reveals the correlations between different vegetable categories and quantifies these correlations using Pearson's correlation coefficient. Subsequently, by integrating time series analysis and multi-objective programming, a mathematical model is constructed, aimed at maximizing profits under specific constraints. The innovation of this research lies in its comprehensive consideration of category-level sales management and the application of modern optimization algorithms for replenishment and pricing strategies. The uniqueness of this paper is in its integrative approach to the vegetable sales problem, providing refined mathematical models and advanced optimization methods. Finally, the paper thoroughly describes the steps of the research design, including sales data analysis, cost markup analysis, and the construction of an optimization model based on time series analysis and multi-objective programming, intending to offer supermarkets a vegetable sales management plan adaptable to market changes.

Automated Pricing and Replenishment Decision Modeling for Supermarket Vegetables

This paper analyzes the historical sales data of vegetable products in a fresh food supermarket, and explores the automatic pricing and replenishment decision-making scheme of vegetable products in this supermarket. Firstly, we integrate and clean the attached data, and then we solve the characteristics and interrelationships of individual products and categories by establishing SARIMA model and Spearman's correlation coefficient model, and then we use nonlinear regression model, nonlinear autoregressive neural network model and optimization model to realize automatic pricing and replenishment decision-making for vegetable products.

Commodity Pricing and Replenishment Decision Strategy Based on the Seasonal ARIMA Model

As a crucial component of enterprise marketing strategy, commodity pricing and replenishment strategies often play a pivotal role in determining the profit of retailers. In pursuit of profit maximization, this work delved into the realm of fresh food supermarket commodity pricing and replenishment strategies. We classified commodities into six distinct categories and proceeded to examine the relationship between the total quantity sold in these categories and cost-plus pricing through Pearson correlation analysis. Furthermore, a Seasonal ARIMA model was established for the prediction of replenishment quantities and pricing strategies for each of the categories over a seven-day period. To ensure precise data, we extended our forecasting to individual products for a single day, employing 0–1 integer programming. To align the inquiry with real-world scenarios, we took into account various factors, including refunds, waste, discounts, and the requirement that individual products fall within specific selling ranges. The results show that the profit will be maximized when the replenishment of chili is 39.874 kg and the replenishment of edible mushrooms is 43.257 kg in the future week. We assume that the residual of the model is white noise. By testing the white noise of the model, the analysis of the residual Q statistic results shows that it is not significant in level, which can prove that the model meets the requirements and the obtained results are reliable. This research provides valuable insights into the realm of commodity pricing and replenishment strategy, offering practical guidance for implementation.

Domestic retailing, supply chain management, and the rise of fresh food supermarkets in China

This study investigates the emergence of fresh food supermarkets and explores domestic retailers’ fresh food supply chain management in China. The study explores two aspects of supply chain management: procurement and logistics. In line with prior research, the results suggest that domestic retailers’ continuous dominance over international retailers stems from their development of supply chain management. This study demonstrates that endogenous creativity fostered the emergence of fresh food supermarkets. Additionally, it underscores the importance of focusing beyond the transplantation route and Western impact when studying supermarkets in less developed countries.

Research on Pricing and Replenishment Strategies of Fresh Food Supermarkets Based on Support Vector Regression and Backpack Problem Modeling

With the improvement of people's living standards, fresh produce superstores are gradually favored by consumers. To better meet the market demand and maximize profits, this paper carries out an in-depth study on the pricing and replenishment strategy of vegetable goods. Firstly, data preprocessing is carried out to ensure its validity and accuracy; secondly, sales patterns are revealed through statistical analysis and clustering methods; furthermore, optimization models and support vector regression are used to predict sales strategies; finally, the optimal combination of commodities is screened out based on the knapsack problem using the greedy algorithm in order to maximize the profitability of the superstore.

Using labelling information to evaluate the distribution of food additives in products marketed in Brazil

Food additives are ingredients added to food and beverages in order to modify physical, chemical, biological or sensory characteristics, contributing to the development of products that are safer and more convenient and attractive. Although they are widely used by food industries, little is known about the distribution of the food additives currently employed in products marketed in Brazil. Therefore, this study aimed to use labelling information of commercial food and beverages in order to identify the substances currently used by the Brazilian industry. For this, 3300 labels of 426 food items described in the Personal Food Consumption module of the Household Budget Survey (POF 2017/2018) of the Brazilian Institute of Geography and Statistics (IBGE) were searched on websites of supermarket chains and food companies as well as by visits to commercial establishments. According to the ingredient lists of the evaluated samples, 186 distinct food additives were identified. The average number of declared substances per product was between 4 and 5, with most of the labels indicating the presence of 2 or 3 additives. Considering the identified substances, 93 had an Acceptable Daily Intake (ADI) not specified or not limited and 89 were additives with a numerical ADI. Citric acid and lecithin were the most frequent substances with ADI not specified or not limited while potassium sorbate and pentasodium triphosphate were the most frequent food additives with numerical ADI. The most frequent combinations found in the evaluated samples were of potassium sorbate and citric acid, and also sodium nitrite, sodium erythorbate, and sodium diphosphate. This study demonstrates the distribution of food additives in products marketed in Brazil, allowing the creation of a comprehensive and unprecedented database, which will contribute to the evaluation of usage trends and future exposure studies for health risk assessment.

Emulsifiers in ultra-processed foods in the UK food supply.

Ultra-processed foods (UPF), including those containing food additive emulsifiers, have received research attention due to evidence implicating them in the pathogenesis of certain diseases. The aims of this research were to develop a large-scale, brand-level database of UPF in the UK food supply and to characterise the occurrence and co-occurrence of food additive emulsifiers. A database was compiled sampling all products from the food categories contributing to energy intake from UPF in the UK from the National Diet and Nutrition Survey (2008-2014). Every food in these categories were identified from online supermarket provision from the 'big four' supermarkets that dominate the market share in the UK, comprising Tesco, Sainsbury's, Asda and Morrisons. Major supermarkets in the UK. A total of 32 719 food products in the UK supermarket food supply were returned in searches. Of these, 12 844 products were eligible and manually reviewed for the presence of emulsifiers. Emulsifiers were present in 6642 (51·7 %) food products. Emulsifiers were contained in 95·0 % of 'Pastries, buns and cakes', 81·9 % of 'Milk-based drinks', 81·0 % of 'Industrial desserts' and 77·5 % of 'Confectionary'. Fifty-one per cent of all emulsifier-containing foods contained multiple emulsifiers. Across emulsifier-containing foods, there were a median of two emulsifiers (IQR 2) per product. The five most common emulsifiers were lecithin (23·4 % of all products), mono- and diglycerides of fatty acids (14·5 %), diphosphates (11·6 %), and xanthan gum and pectin (8·0 %). Findings from this study are the first to demonstrate the widespread occurrence and co-occurrence of emulsifiers in UPF in the UK food supply.

Unhealthy food availability, prominence and promotion in a representative sample of supermarkets in Flanders (Belgium): a detailed assessment

IntroductionThe supermarket food environment is a key setting for potential public health interventions. This study assessed food availability, prominence and promotion in a representative sample of supermarkets in Flanders (Belgium).MethodsA sample of 55 supermarkets across five chains and 16 Flemish municipalities was selected in 2022, about 64% in the most deprived socioeconomic areas. Healthiness indicators related to food availability (ratio of cumulative linear shelf length for healthy versus unhealthy foods), prominence (proportion of unhealthy foods at check-outs and end-of-aisle endcaps), and promotion (food marketing on food packages) were measured.ResultsOverall, the average ratio of healthy/unhealthy foods in supermarkets in Flanders was 0.36, meaning that for every 10m of shelf length of unhealthy foods there was 3.6m of healthy foods. There was a large variation in ratio’s across supermarket chains. Of all foods available, 97.5% were ultra-processed at the check outs, while 72.2% and 58.5% were ultra-processed at the front and back end-of-aisle end-caps, respectively. Confectionery and sweet biscuits were the food categories with on average the highest number of marketing messages on pack per 10m of shelf length.ConclusionSupermarket in-store food environments in Flanders were found generally unhealthy, with those located in low income areas having unhealthier in-store food environments than supermarkets located in medium and high income areas. Despite commitments of all large supermarket chains in Flanders to promote and create healthier in-store food environments, our findings indicate that currently consumers are incentivized to buy unhealthy rather than healthy food products.

Changes in Policy Supports for Healthy Food Retailers, Farmers Markets, and Breastfeeding Among US Municipalities, 2014-2021: National Survey of Community-Based Policy and Environmental Supports for Healthy Eating and Active Living (CBS-HEAL).

Policies and practices at the local level can help reduce chronic disease risk by providing environments that facilitate healthy decision-making about diet. We used data from the 2014 and 2021 National Survey of Community-Based Policy and Environmental Supports for Healthy Eating and Active Living to examine prevalence among US municipalities of policies to support access to healthier food in supermarkets, convenience stores, and farmers markets, as well as policies to support breastfeeding among government employees. Chi-square tests were conducted to compare prevalence estimates from 2021 to 2014 overall and according to municipal characteristics. In 2021, 29% of municipalities had at least 1 policy to encourage full-service grocery stores to open stores, which was not significantly different from 31% in 2014. Prevalence of having at least 1 policy to help corner stores sell healthier foods declined significantly from 13% in 2014 to 9% in 2021. Prevalence of policies providing all local government employees who were breastfeeding breaktime and space to pump breast milk increased significantly from 25% in 2014 to 52% in 2021. The percentage of municipalities that provided 8 or more weeks of paid maternity leave for employees increased significantly from 16% in 2014 to 19% in 2021. Prevalence of supports for supermarkets, convenience stores, and farmers markets generally did not increase among US municipalities from 2014 to 2021, while some supports for breastfeeding among municipal employees increased during this time. Opportunities exist to improve municipal-level policies that support healthy eating and breastfeeding among community residents and employees.

The Association Between Dietary Quality Indicators from Supermarket Food Purchases and Multiple Days of Dietary Recall

The Association Between Dietary Quality Indicators from Supermarket Food Purchases and Multiple Days of Dietary Recall