Average Order Value Research Articles

Understanding Age-Driven Preferences: A Weighted Sum Analysis of Consumer Behavior in E-commerce

Consumer activity in online commerce plays a crucial role in modern business functions, impacting market trends and guiding approaches for digital merchants. This research utilizes the weighted sum technique to assess consumer actions among different age brackets, emphasizing significant indicators like Average Order Value, Satisfaction with Customer Support, Timeliness of Delivery, and Rate of Product Returns. The results underscore unique preferences and performance patterns across age segments, offering actionable intelligence for e-commerce enterprises aiming to refine their tactics. The examination indicates that individuals aged 45-54 stand out as the leading performers across every metric, showcasing the highest expenditure, most satisfactory customer support ratings, swiftest delivery times, and minimal product return rates. Conversely, the 35-44 age bracket displays the lowest overall performance, marked by comparatively lower spending, moderate satisfaction with customer support, extended delivery durations, and elevated rates of product returns. Intermediate groups include the 18-24 and 55-65 age groups, with the former showing strong overall performance and the latter displaying good customer support satisfaction and reasonable delivery times but lower spending and slightly higher return rates compared to the top performers. Additionally, the 25-34 age group performs moderately well, with decent customer support satisfaction and delivery times but lower spending and higher product return rates. These findings provide invaluable direction for e-commerce enterprises aiming to customize their strategies adeptly for diverse age segments. By comprehending the unique preferences and actions of each demographic, businesses can refine their online shopping offerings, elevate customer contentment, bolster retention figures, and foster comprehensive advancement within the competitive e-commerce.

Development of new payment services and the role of the fintech sector during the COVID-19 pandemic

Purpose: The purpose of the article is to present both theoretical and practical basis for development of payment services in Poland and in the whole world during the COVID-19 pandemic. Over this time there was a sharp rise in e-commerce along with a fast growth of the number of consumers making online payments. This resulted in changes in adoption of new technologies and payment services. Apart from those which were the consequence of quickening the pace of change in the consumers’ behavior, a crucial role, especially in developing countries, was played by local regulators, who somehow forced financial institutions to create new solutions, which fintech readily made good use of. In numerous countries it fostered radical and groundbreaking quickening of the pace of shifting to electronic payments and creating a new sort of payment services, adjusted to the needs and expectations of younger consumers. Methodology: The paper uses the method of an economic analysis and literature review - mostly electronic sources, descriptive and comparative analyses. Findings: From customers’ perspective, the impact of COVID-19 pandemic on development of new payment services should be acknowledged as positive, or even groundbreaking in some developing countries. Over the years 2020-2021 the number of customers making on-line payments, especially mobile payments, grew rapidly. This was the result of a fast, forced by pandemic, growth in sales in e-commerce. Consequently, it enabled to introduce and widely promote new financial services - based on open banking, and promoting solutions targeted at young consumers, e.g. deferred payments. Even though the pandemic is over, the interest rate rise and the consequences of the war in Ukraine are bound to bring further, dynamic development of such payment services, as well as their popularization on more and more new markets all over the world. Practical implications: The analysis of relations between theoretical and practical bases of widespread adoption of new solutions concerning on-line payments in the world during the COVID-19 pandemic is an important factor in the development of e-commerce market and financial services. The fact that digital forms of payments have become very common brought about the network effect, a situation when the value for the customer depends on the number of users of a particular solution. Due to that, poorer, developing countries could, making use of the solutions based on open banking and the technology provided by fintech, quickly popularize cashless, and electronic payments. Only a few years ago it was estimated that in the countries lacking the standard payment infrastructure it would take decades to reach this level. Also, in developed countries the pandemic contributed to popularization among young consumers of solutions adapted to their preferences, being an alternative to traditional credit cards. Deferred payments are a solution which is commonly used in e-commerce, and their main merits include increasing both conversion rates and average order value. However, it needs to be emphasized that this goes with a less flexible business model of the companies providing such services in high interest rate environment, as well as adverse consequences of broad access to such services. Many countries have observed a growth of customer debt - which effects both credit worthiness and problems to pay off rising debts. This results in imposing formal regulations on deferred payments markets more and more frequently.

Enhancing Customer Experience in E-Commerce Through AI-Powered Personalization: A Case Study

Aim: This study is intended to engage in the in-depth study of AI-enabled personalization tactics on the quality of customer experience as competition informs the e-commerce environment. The research employs a case study assessment of a prominent world-wide retailer with the primary aim of revealing the dominant influence of cutting-edge AI personalisation technology in actual applications. Methods: The study applied the mixed-methods research, which was made up of quantitative as well as qualitative research techniques such as sound data analysis and field research approaches to arrive at a comprehensive apprehension of the phenomenon. Data science system features such as studying key customer behaviour metrics, conversions, average order, customer value, and satisfaction, appreciate the company's case from superior data systems. The qualitative side of this study was indicated through the revelation of in-depth interviews that were done with a group of educated customers and an extensive online survey that was designed to capture their preferences, opinions, and perceptions in relation to the personalized shopping experience(Gao & Liu, 2022b). Results: The result shown a superlative boost in a lot of customer experience metrics, such as loyalty, proactivity, predictability, and automation, after the execution of the advanced AI personalization engine. What need to be prominently mentioned is an increase of conversion rate which saw a hike by 25% endorsing the fact that now, more customers on the site would complete their purchase process. Also, there was a remarkable 17% increase in the average order value, showing that personalized suggestions and tailor-made experiences had an impact on how customers would spend more per time they place an order. Customer’s life-time value (CLV) was extended by 12%. User stayed loyal and engaged for the longer time period. This probably was the most impressive outcome of the brand's satisfaction scores, as the jumps of them by 22% show the improvement of the customer experience overall. The analysis of qualitative data reveals that consumers experience genuine appreciation of the personalized shopping experience they get from being offered items that match their personal attributes such as the in-depth interpretations of customer likes and dislikes which the algorithm platform uses, quick discovery of products with minimal scrolling, saving of the time used in the search phase, and emotional closeness to freedom/ your identity, in the case of fashion (Raji et al., 2021). Conclusion: This comprehensive case study provides compelling evidence of the transformative potential of AI-powered personalization in enhancing customer experience within the e-commerce landscape. By leveraging advanced machine learning algorithms and vast customer data repositories, businesses can deliver highly tailored content, product recommendations, and optimized search results that resonate deeply with individual customer preferences and needs. The findings demonstrate that implementing AI personalization strategies can drive improved customer engagement, increased sales, and foster long-term loyalty, ultimately conferring a significant competitive advantage in the rapidly evolving e-commerce industry.

The Effect of the Entrepreneurial Ecosystem of Universities on the Innovative Activity in Russian Regions

The entrepreneurial ecosystem of universities is frequently recognized to have a key influence on the innovative activity of the related regions. However, these relationships have not been explored in the scientific literature regarding Russia. Therefore, the current study aims to determine and identify the contours of the entrepreneurial ecosystem of domestic universities in terms of the innovative activity of subjects in Russian regions. The methodological toolkit covers methods for information processing such as monographic desk research, hierarchical cluster and correlation analyses, and comparative analysis. Applying a hierarchical cluster analysis, we grouped universities according to the level of entrepreneurial activity with the allocation of the average value in order to determine the existing correlations and elucidate the problems in involving university innovations in the ratings of innovative activity of regions. The results contribute to the development of existing approaches toward the study of the entrepreneurial ecosystems of universities through a deeper understanding of their role in stimulating the innovative activity of regions and transformation processes.

An EEG‐based neuro‐recommendation system for improving consumer purchase experience

AbstractThe aperture between the marketing domain and the electroencephalography (EEG)‐based brain–computer interface (BCI) has been achieved with the inception of neuromarketing. This domain helps access the hidden information of the preferences and tastes of the consumers who intend to purchase. Research scholars have experimented with this emerging area in multiple aspects like designing pricing, promotions, predicting purchase‐related activities, new product development, and so on. In this study, we have proposed an innovative use of neuromarketing to build a recommendation system. This recommendation system can potentially suggest suitable products to the consumer based on the past purchase behavior. This proposal carries huge potential in converting visitors to shoppers, increasing average order value, increasing the number of items per order, designing personalized promotions, and so on. The commonality of activated brain signals has been used to build this recommendation system. This neuromarketing‐based recommendation system carries the advantage over the traditional recommendation system as this system suggests products based on the actual real‐time state of the brain during the purchase. This system successfully initiated the starting point of building a neuromarketing‐based recommendation system.

A study on data augmentation in voice anti-spoofing

In this paper we perform an in depth study of how data augmentation techniques improve synthetic or spoofed audio detection. Specifically, we propose methods to deal with channel variability, different audio compressions, different bandwidths and unseen spoofing attacks. These challenges, have all been shown to significantly degrade the performance of audio based systems and anti spoofing systems. Our results are based on the ASVspoof 2021 challenge, in the Logical Access (LA) and Deep Fake (DF) categories. Our study is Data-Centric, meaning that the models are fixed and we significantly improve the results by manipulating the data. We introduce two forms of data augmentation - compression augmentation for the DF part, and compression and channel augmentation for the LA part. In addition, we introduce a double sided log spectrogram feature design that improves the results significantly by centering the sub-bands of interest, where the discriminating spoofing artifacts can be localized. Furthermore, a new type of online data augmentation, SpecAverage, is introduced. This method includes masking the audio features with their average value in order to improve generalization. Our best single system and fusion schemes both achieve state of the art performance in the DF category, with an EER of 15.46% and 14.27%, respectively. Our best system for the LA task reduced the best baseline EER by 50% and the min t-DCF by 16%. Our techniques to deal with spoofed data from a wide variety of distributions can be replicated and can help anti spoofing and speech based systems enhance their results.

Transportation of Raw Materials, Recondite Question in Manufacturing Enterprise

Based on the optimization theory, this paper studies the mathematical modeling problem related to the ordering and transportation of raw materials. The paper starts with reasonable assumptions, based on which the following factors are used as index: “average supply”, “order completion rate”, “average order value” and “standard deviation of supply” of each supplier, and the weight of each index is determined by using entropy weight method. On the premise of reasonable weight, the distance method of good-bad solutions (TOPSIS) is used to evaluate and rank each supplier, and finally, the most important supplier is selected. Then, a 0-1 programming model is established, in which “minimum order price” and “minimum loss” are taken as the objective functions, and the two-week inventory of the enterprise is combined with factors such as the loss rate of the forwarder, using MATLAB programming TOPSIS algorithm to solve the model to obtain the optimal ordering and transshipment plan. Considering the possibility that the enterprise needs low utilization of raw materials A and C, a bi-objective programming model is established to determine the weekly ordering and transshipment plan within the target weeks. On the other hand, when the number of suppliers is sufficient, the capacity of the forwarders limits the expansion of the capacity of the enterprise. Therefore, combined with the existing data, a linear programming model with the maximum production capacity as the objective function is established to obtain the maximum production capacity and formulate ordering and transshipment schemes. Finally, the solution process and results are summarized and analyzed.

Новый подход к применению метода измерения напряженности электрического поля по среднему значению

The paper considers a new possibility of using the method of measuring the electric field strength by an average value in order to reduce the error from the inhomogeneity of the field and expand the spatial range of measurements. The studies carried out in the work allowed us to establish that when using the measurement method by the average value, there are always three values at each measurement step, two of which correspond to the two previous values of the EP intensity determined with errors opposite in sign, and the third corresponds to the average value of them. Therefore, in the work, it is proposed to measure the electric field strength at one point in space by two sensors with errors opposite in sign. At the same time, alternately determining at each step of averaging the average value of the EP intensity from the previously obtained and subsequent average values, bringing the measurement result closer to the true value. Based on the results of theoretical research, a new method is proposed — the "Measurement method with step-by-step averaging", which, without complicating the measurement process, makes it possible to reduce by two to three times the error in measuring the intensity of inhomogeneous electric fields in a wide spatial range compared with the measurement method by the average value.

Retail atmospherics effect on store performance and personalised shopper behaviour: a cognitive computing approach

PurposeThe best possible way for brick-and-mortar retailers to maximise engagement with personalised shoppers is capitalising on intelligent insights. The retailer operates differently with diversified items and services, but influencing retail atmospheric on personalised shoppers, the perception remains the same across industries. Retail atmospherics stimuli such as design, smell and others create behavioural modifications. The purpose of this study is to explore the atmospheric effects on brick-and-mortar store performance and personalised shopper's behaviour using cognitive computing based in-store analytics in the context of emerging market.Design/methodology/approachThe data are collected from 35 shoppers of a brick-and-mortar retailer through questionnaire survey and analysed using quantitative method.FindingsThe result of the analysis reveals month-on-month growth in footfall count (46%), conversation rate (21%), units per transaction (27%), average order value (23%), dwell time (11%), purchase intention (29%), emotional experience (40%) and a month-on-month decline in remorse (20%). The retailers need to focus on three control gates of shopper behaviour: entry, browsing and exit. Attention should be paid to the cognitive computing solution to judge the influence of retail atmospherics on store performance and behaviour of personalised shoppers. Retail atmospherics create the right experience for individual shoppers and forceful use of it has an adverse impact.Originality/valueThe paper focuses on strategic decisions of retailers, the tactical value of personalised shoppers and empirically identifies the retail atmospherics effect on brick-and-mortar store performance and personalised shopper behaviour.

A Study on Optimistic need of Artificial Intelligence in Fashion Retail Industry

The fashion e-commerce market has been growing steadily in the past few years accounting for USD 371 billion or 21% retail sales of apparel and footwear globally in 2019. But as most of the worlds are experiencing self-isolation and lockdown measures, the corona virus crisis is pushing brands to digitalize even faster to survive, engage with customers, designers, manufactures and redesign their supply chain operations. Many sectors are reeling from the fallout of the COVID-19 pandemic as they stare into the abyss of the impending recession and fashion has not been immune. But aside from economic factors, the industry is also facing lasting structural change. Artificial Intelligence optimizes conversion, Average Order Value (AOV) and repeat purchase rate by understanding a customer’s preferences and suggesting the right products and outfits for them. Recommendations are tailored to the physical stores with latest technologies by implementing virtual trail room, regional trends, as well as the customers’ body type, color, desired occasions and personal style.

Analytics for labor planning in systems with load-dependent service times

This paper presents a generalized framework for labor planning in systems with load-dependent service times. Our approach integrates customer arrival forecasting, service time estimation, and staffing into an end to end process. More specifically, (i) we propose a hybrid model to forecast customer arrivals, that combines a traditional time-series technique with a state-of-the-art machine learning algorithm, thereby allowing to incorporate a rich set of predictors; (ii) we develop a methodology to estimate the distribution of load-dependent service times from past transactions data; and (iii) we present a stochastic programming formulation to determine staffing levels under quality-of-service constraints. Finally, we develop a heuristic solution algorithm that utilizes an embedded discrete event simulation to evaluate system performance.To demonstrate the practical applicability of our approach, we conduct a case study at a franchisee of a major international fast food chain. Our data set includes the number of transactions, average order value, average service times, and staffing levels recorded at the restaurant on an hourly level, as well as information on marketing activities of the fast food chain on a daily level for nine consecutive years. We show that by applying our approach, the personnel expenses could be reduced by 4.4%, which would translate into an increase in earnings before interest and taxes by 13% at the collaborating restaurant.

Analysis of the dynamics of expenditures on pharmaceutical support of population in Ukraine, Belarus republic and in European Union

Aim: comparative analysis the dynamics of changes in the indices of expenditures (%) on pharmaceutical provision of population from total health expenditure at the macroeconomic level in Ukraine, the Republic of Belarus (RB) and the countries of the European Union (EU). Materials and methods. The studies used data from the World Health Organization and its Regional Office for Europe, as well as data from the legislative and regulatory framework regulating medical and pharmaceutical activities in Ukraine, the Republic of Belarus and the EU. Historical, analytical-comparative, systemic, logical, graphic, mathematical-statistical methods of scientific search and knowledge were used. Results. It has been established that in the group of reference countries, the expenditures indicator (%) for the pharmaceutical provision of the population from the total spending on health during the period of 1990-2015 fluctuated in a wide range of values. The largest range of values was typical for Belarus (from 3.2 % in 1992 to 29.8 % in 2015), and the smallest for the EU countries (from 16.7 % in 2011 to 18.8 % according to 2003 data). Analyzing the dynamics of changes in this indicator, it was established that there was a tendency towards its decline across the EU and Ukraine, while in Belarus, on the contrary, it was increasing. Thus, in 2015, this indicator increased by 2.5 times, compared with the base data in the 1990 analysis. By the average value in order of magnitude of the indicator that was analyzed, the reference countries were located as follows: Ukraine (10.82 %); RB (14.87 %); EU countries (17.88 %). Conclusions. A significant fluctuation in the values of expenditures (%) allocated for pharmaceutical provision of the population in total health expenditures in the group of countries that were studied was established. In addition, the unstable nature of changes in the indicator that was analyzed in Belarus indicates the need for further research in this direction.

Personalized digital marketing recommender engine

E-business leverages digital channels to scale its functions and services and operates by connecting and retaining customers using marketing initiatives. To increase the likelihood of a sale, the business must recommend additional items that the customers may be unaware of or may find appealing. Recommender Engine (RE) is considered to be the preferred solution in these cases for reasons that include delivering relevant items, hence improving cart value, and boosting customer engagement. The paper describes a model for delivering real-time, personalised marketing information concerning the recommended items for online and offline customers, using a blend of selling strategies: up-selling, cross-selling, best-in-class-selling, needs-satisfaction-selling and consultative-selling. The model further defines the e-marketplace by clustering items, customers and unique selling proposition (USP), and then gathering, storing, and processing transactional data, and displaying personalised marketing information to support the customer in their decision-making process, even when purchasing from large item spaces. An experimental study using a quantitative research methodology was conducted in a mid-size healthcare retailer, based out of India, to determine the tangible benefits. The model was tested with 100 online customers and, with the adoption of the proposed methodology, the results indicated growth in average monthly revenue (33.49%), Average Order Value (AOV) (32.79%) and Items per Order (IPO) (1.93%).

Using Human Factor Cepstral Coefficient on Multiple Types of Voice Recordings for Detecting Patients with Parkinson's Disease

In this study, we wanted to discriminate between two groups of participants (patients with Parkinson's disease and healthy people) by analyzing 3 types of voice recordings. Firstly we collected multiple types of voice recording of three sustained vowels /a/, /o/ and /u/ at a comfortable level which was collected from the 40 participants (20 PD and 20 healthy). The technique used in this study is to extract Human Factor Cepstral Coefficients (HFCC). The extracted HFCC were compressed by calculating their average value in order to get the Voiceprint from each voice recording. Subsequently, a classification method was performed using Leave One Subject Out validation scheme along with supervised learning classifiers. We used SVM with its four different kernels (RBF, Linea, Polynomial and MLP), and k-nearest neighbored (k=3, 5 and 7). Based on the research result, the best obtained classification accuracy was 87.5% using linear kernel of SVM with the first 14 cepstral coefficients of the HFCC and 100% using the test database.

A/B Testing Measurement Framework for Recommendation Models Based on Expected Revenue

We provide a method to determine whether a new recommendation system improves the revenue per visit (RPV) compared to the status quo. We achieve our goal by splitting RP V into conversion rate and average order value (AOV). We use the two-part test suggested by Lachenbruch to determine if the data generating process in the new system is different. In cases that this test does not give us a definitive answer about the change in RPV, we propose two alternative tests to determine if RPV has changed. Both of these tests rely on the assumption that non-zero purchase values follow a log-normal distribution. We empirically validate this assumption using data collected at different points in time from Staples.com. On average, our method needs a smaller sample size than other methods. Furthermore, it does not require any subjective outlier removal. Finally, it characterizes the uncertainty around RPV by providing a confidence interval.

Analysis of multiple types of voice recordings in cepstral domain using MFCC for discriminating between patients with Parkinson’s disease and healthy people

In this study, we wanted to discriminate between two groups of people. The database used in this study contains 20 patients with Parkinson’s disease (PD) and 20 healthy people. Three types of sustained vowels (/a/, /o/ and /u/) were recorded from each participant and then the analyses were done on these voice samples. The technique used in this study is to extract voiceprint from each voice samples by using mel frequency cepstral coefficients (MFCCs). The extracted MFCC were compressed by calculating their average value in order to extract the voiceprint from each voice recording. Subsequently, a classification method was performed using leave one subject out (LOSO) validation scheme along with support vector machines (SVMs). We also used an independent test to validate our results by using another database which contains 28 PD patients. Based on the research result, the best obtained classification accuracy using LOSO on the first dataset was 82.50 % using MLP kernel of SVM on sustained vowel /u/. And the maximum classification accuracy using the independent test was 100 % using sustained vowel /a/ with polynomial kernel of the SVM and with MLP kernel of the SVM. This result was also achieved using sustained vowel /o/ with polynomial kernel of the SVM.

Impact of Value‐Added Service Features in e‐Retailing Processes: An Econometric Analysis of Web Site Functions

ABSTRACTWe examine the impact of three classes of Web site functions (foundational, customer‐centered, and value‐added) upon e‐retailer performance. Using secondary panel data for 2007–2009 on operating characteristics of over 600 e‐retailers, our econometric analysis finds that only the value‐added service functions are positively associated with changes in e‐retail sales revenues across time. We also observe a decreasing marginal impact of deploying additional value‐added service features. To account for possible alternate explanations, we control for firm‐ and time‐specific fixed effects, merchant types, merchandise categories, and order fulfillment strategies. By further decomposing e‐retail sales revenues into Web site traffic, conversion rate, and average order value, we find that Web site functions affect e‐retail sales revenues mainly through their impact on Web site traffic. Our investigation demonstrates the empirical research usefulness of the Voss conceptual e‐service sand cone model. Our results identify for managers where to focus ongoing e‐retailing system development efforts, yet suggest that focusing too many retailing capabilities on exploratory and experimental value‐added service features may backfire, potentially leading to worsening e‐retailer performance.

Real time: The next frontier for analytics

In 1999, ‘The Cluetrain Manifesto’ warned that ‘markets are conversations’. Today, some 15 years later, software, hardware, mobile and social media vendors have come together to provide tools that allow companies to join and manipulate the conversation. This paper provides a quick overview of the available hardware and software solutions; a discussion of the in-memory landscape, including the strengths and weaknesses of the competing products; and a summary of the latest developments in the social media monitoring space. Given the importance of personalisation and one-to-one advertising for increasing traffic, raising customer conversion rates and increasing average order value, these systems can either be a company’s best friend or its worst enemy.

A critical look at organic photovoltaic fabrication methodology: Defining performance enhancement parameters relative to active area

With the ever-increasing focus on obtaining higher device power conversion efficiencies (PCEs) for organic photovoltaics (OPV), there is a need to ensure samples are measured accurately. Reproducible results are required to compare data across different research institutions and countries and translate these improvements to real-world production. In order to report accurate results, and additionally find the best-practice methodology for obtaining and reporting these, we show that careful analysis of large data sets can identify the best fabrication methodology. We demonstrate which OPV outputs are most affected by different fabrication or measurement methods, and identify that masking effects can result in artificially-boosted PCEs by increasing fill factor and current densities, requiring care when selecting which mask to use. For example, our best performing devices (>6% efficiency) show that the smallest mask areas have not produced a surfeit of the highest performers, with only 11% of the top performing devices measured using a 0.032cm2 mask area, while 44% used the largest mask (0.64cm2). This trend holds true for efficiencies going down to 5%, showing that effective fabrication conditions are reproducible with increasing mask areas, and can be translated to even larger device areas. Finally, we emphasise the necessity for reporting the best PCE along with the average value in order to implement changes in real-world production.