A Systematic Review of Machine Learning Approaches for Customer Lifetime Value Prediction in E-Commerce

We describe the Customer LifeTime Value (CLTV) prediction system deployed at ASOS.com, a global online fashion retailer. CLTV prediction is an important problem in e-commerce where an accurate estimate of future value allows retailers to effectively allocate marketing spend, identify and nurture high value customers and mitigate exposure to losses. The system at ASOS provides daily estimates of the future value of every customer and is one of the cornerstones of the personalised shopping experience. The state of the art in this domain uses large numbers of handcrafted features and ensemble regressors to forecast value, predict churn and evaluate customer loyalty. Recently, domains including language, vision and speech have shown dramatic advances by replacing handcrafted features with features that are learned automatically from data. We detail the system deployed at ASOS and show that learning feature representations is a promising extension to the state of the art in CLTV modelling. We propose a novel way to generate embeddings of customers, which addresses the issue of the ever changing product catalogue and obtain a significant improvement over an exhaustive set of handcrafted features.

Accurately predicting Customer Lifetime Value (CLV) is paramount in optimizing customer relationship management. This study introduces a novel deep learning approach, employing a neural network model to forecast CLV for a leading international e-commerce retailer. This investigation delves into the interplay of key performance indicators—Net Promoter Score (NPS), Average Transaction Value (ATV), and Customer Effort Score (CES)—and their collective impact on CLV. The research utilized a dataset of 15,000 customer profiles and crafted a sequential neural network with dense layers optimized through hyperparameter tuning and regularization to thwart overfitting. The model's efficacy was assessed on a 10 % test set, revealing its adeptness at capturing intricate, nonlinear predictor-customer lifetime value (CLV) relationships. Consistency in training and test performance metrics underscored the model's generalizability, while high R-squared and explained variance scores confirmed the predictive strength of the chosen factors. This research seeks to provide a solution for building an artificial intelligence model with an artificial neural network algorithm to predict customer lifetime value. By incorporating this principle, the study aims to leverage the power of neural networks to forecast CLV, enabling retailers to make informed decisions and optimize customer relationships accurately. This study finds that Net Promoter Score (NPS) and Customer Effort Score (CES) have a powerful impact on the neural network model's ability to predict Customer Lifetime Value (CLV) accurately. On the other hand, while Average Transaction Value (ATV) exhibits the least impact, it still significantly contributes to the accuracy of Customer Lifetime Value (CLV) predictions. These results underscore the importance of incorporating customer feedback metrics like NPS and CES when building predictive models for CLV estimation. Integrating critical customer metrics into neural networks gives retailers enhanced insights, enabling precise customer segmentation, resource allocation, and strategic growth. The study paves the way for future research to refine further CLV prediction, including dataset expansion, customer profile enrichment, and prescriptive marketing optimization.

Accurate customer LifeTime Value (LTV) predictions are crucial for customer relationship management, especially in Supply Chain Platforms (SCP), which involve effectively managing the service resources in business decision-making. Previous LTV prediction methods usually rely on ample historical customer data, which is not available in the early stages of a customer's lifecycle. It makes the modeling of the historical customer data a difficult task due to the data sparsity. Besides, the long-tail distribution of customer LTV also brings new challenges to the prediction of LTV. To tackle the above issues, we propose CDLtvS, a novel Cross Domain method for customer Lifetime value prediction in SCP. It leverages rich cross-domain information from upstream platforms to enhance LTV predictions in downstream platforms. Firstly, CDLtvS pre-trains the customer representations by an LTV modeling framework named LtvS in source and target domains separately. Specifically, LtvS incorporates the Expert Mask Network (ExMN), which not only effectively models the long-tail distribution of LTV in single-domain but also resolves cross-domain learning model bias resulting from this distribution. Then, the various-level alignment mechanism is introduced to keep the consistency of knowledge transferring from source to target domains on both sparse and non-sparse data. Comprehensive experiments on real-world data from JD, one of the world's largest supply chain platforms, demonstrate that CDLtvS achieves a normalized mean average error of 0.3378 in LTV prediction, outperforming 16.3% to the baseline. Additionally, the improvements of ≥2.3% across various data sparsity levels (0% -- 80%) provide valuable insights into cross-domain LTV modeling.

The Internet of Things (IoT) has transformed many aspects of modern life, from healthcare and transportation to home automation and industrial control systems. However, the increasing number of connected devices has also led to an increase in security threats, particularly from botnets. To mitigate these threats, various machine learning (ML) and deep learning (DL) techniques have been proposed for IoT botnet attack detection. This systematic review aims to identify the most effective ML and DL techniques for detecting IoT botnets by delving into benchmark datasets, evaluation metrics, and data pre-processing techniques in detail. A comprehensive search was conducted in multiple databases for primary studies published between 2018 and 2023. Studies were included if they reported the use of ML or DL techniques for IoT botnet detection. After screening 1,567 records, 25 studies were included in the final review. The findings suggest that ML and DL techniques show promising results in detecting IoT botnet attacks, outperforming traditional signature-based methods. However, the effectiveness of the techniques varied depending on the dataset, features, and evaluation metrics used. Based on the synthesis of the findings, this review proposes a taxonomy for ML and DL techniques in IoT botnet attack detection and provides recommendations for future research in this area. This review illuminates the considerable potential of ML and DL approaches in bolstering the detection of IoT botnet attacks, thereby offering valuable insights to researchers involved in the domain of IoT security.

With the development of information and technology, especially with the boom in big data, healthcare support systems are becoming much better. Patient data can be collected, retrieved, and stored in real time. These data are valuable and meaningful for monitoring, diagnosing, and further applications in data analysis and decision-making. Essentially, the data can be divided into three types, namely, statistical, image-based, and sequential data. Each type has a different method of retrieval, processing, and deployment. Additionally, the application of machine learning (ML) and deep learning (DL) in healthcare support systems is growing more rapidly than ever. Numerous high-performance architectures are proposed to optimize decision-making. As reliability and stability are the most important factors in the healthcare support system, enhancing the predicted performance and maintaining the stability of the model are always the top priority. The main idea of our study comes from ensemble techniques. Numerous studies and data science competitions show that by combining several weak models into one, ensemble models can attain outstanding performance and reliability. We propose three deep ensemble learning (DEL) approaches, each with stable and reliable performance, that are workable on the above-mentioned data types. These are deep-stacked generalization ensemble learning, gradient deep learning boosting, and deep aggregation learning. The experiment results show that our proposed approaches achieve more vigorous and reliable performance than traditional ML and DL techniques on statistical, image-based, and sequential benchmark datasets. In particular, on the Heart Disease UCI dataset, representing the statistical type, the gradient deep learning boosting approach dominates the others with accuracy, recall, F1-score, Matthews correlation coefficient, and area under the curve values of 0.87, 0.81, 0.83, 0.73, and 0.91, respectively. On the X-ray dataset, representing the image-based type, the deep aggregation learning approach shows the highest performance with values of 0.91, 0.97, 0.93, 0.80, and 0.94, respectively. On the Depresjon dataset, representing the sequence type, the deep-stacked generalization ensemble learning approach outperforms the others with values of 0.91, 0.84, 0.86, 0.8, and 0.94, respectively. Overall, we conclude that applying DL models using our proposed approaches is a promising method for the healthcare support system to enhance prediction and diagnosis performance. Furthermore, our study reveals that these approaches are flexible and easy to apply to achieve optimal performance.

Transcranial magnetic stimulation (TMS) combined with electroencephalography (EEG) provides a powerful framework to probe and modulate human cortical and corticospinal excitability. In recent years, brain state-dependent EEG–TMS paradigms have gained increasing interest by synchronizing stimulation to ongoing neural activity. However, traditional approaches relying on single oscillatory features or fixed thresholds have yielded heterogeneous and often inconsistent results, motivating the adoption of machine learning (ML) and artificial intelligence (AI) methods to model brain state in a multivariate, data-driven manner. This review synthesizes current ML and deep learning (DL) approaches aimed at predicting cortical and corticospinal excitability from pre-stimulus EEG. We contextualize these methods within brain state-dependent EEG–TMS frameworks based on oscillatory phase, power, and network-level features, and within evolving definitions of brain state that move beyond local biomarkers toward distributed, large-scale, and dynamically evolving neural representations. The reviewed studies span feature-engineered models, data-driven decoding approaches, and emerging adaptive closed-loop frameworks. Finally, we discuss key methodological challenges, translational barriers, and future directions toward personalized, interpretable, and fully closed-loop neuromodulation systems.

Contemporarily, two emerging techniques, blockchain, and machine learning are driving dramatic rapid growth in the field of network security. This paper describes a literature review of machine learning approaches for network security analytics and summarizes some applications of blockchain in the field of network security. We first illustrate three types of network security data, including network traffic, software binary, and security logs. Then we discuss the application of machine learning and deep learning approaches to analyze these data. We cover a broad array of attack types, including malware, spam, insider threats, network intrusions. We also summarize some applications and potential development direction of blockchain technology.

Passive non-invasive sensing signals from wearable devices and smartphones are typically collected continuously without user input. This passive and continuous data collection makes these signals suitable for moment-by-moment monitoring of health-related outcomes, disease diagnosis, and prediction modeling. A growing number of studies have utilized machine learning (ML) approaches to predict and analyze health indicators and diseases using passive non-invasive signals collected via wearable devices and smartphones. This systematic review identified peer-reviewed journal articles utilizing ML approaches for digital phenotyping and measuring digital biomarkers to analyze, screen, identify, and/or predict health-related outcomes using passive non-invasive signals collected from wearable devices or smartphones. PubMed, PubMed with Mesh, Web of Science, Scopus, and IEEE Xplore were searched for peer-reviewed journal articles published up to June 2024, identifying 66 papers. We reviewed the study populations used for data collection, data acquisition details, signal types, data preparation steps, ML approaches used, digital phenotypes and digital biomarkers, and health outcomes and diseases predicted using these ML techniques. Our findings highlight the promising potential for objective tracking of health outcomes and diseases using passive non-invasive signals collected from wearable devices and smartphones with ML approaches for characterization and prediction of a range of health outcomes and diseases, such as stress, seizure, fatigue, depression, and Parkinson’s disease. Future studies should focus on improving the quality of collected data, addressing missing data challenges, providing better documentation on study participants, and sharing the source code of the implemented methods and algorithms, along with their datasets and methods, for reproducibility purposes.

Identifying and selecting the most profitable customers from a shareholder’s perspective is of great interest to marketing managers. One promising line in this regard is to explore the customer lifetime value and its profitable management over time. There is a significant body of marketing literature about CLV evaluation in terms of various perspectives. However, much less attention has been paid to the risk associated with customer relationships. Previous researches in this area considered risk as “variability of cash flows generated by customers”, regardless of the trend of variability. Whereas the upside and downside variability from the customer’s expected profitability are extremely different in CRM context. This paper provides a quantitative model based on downside Capital Asset Pricing Model (D-CAPM) to evaluate riskadjusted CLV and compares the results by employment of traditional CAPM. This paper contributes to this field by extending the discussion on customer risk measurement and provides an approach that enables marketing managers to evaluate the risk of decline from average profitability for different customer segments.

A clustering-based nonlinear ensemble (CNE) learning approach is proposed in this paper to forecast exchange rates. In the proposed CNE learning approach: 1) a self-organizing map neural network is introduced to cluster the in-sample component forecasts; 2) kernel-based extreme learning machine is employed to calculate the in-sample ensemble weights for each cluster; and 3) the corresponding clusters’ in-sample ensemble weights are used for out-of-sample component forecasts to obtain the ensemble forecasts. To illustrate and verify the effectiveness of our proposed model, we test its directional and level forecasting accuracy using four major exchange rates. The out-of-sample forecasting performance results show that the proposed CNE learning approach consistently outperforms the component models and other ensemble learning approaches in terms of the directional forecasting accuracy and the level forecasting accuracy.

Incorporating embedded energy resources (EERs) into demand-side management (DSM) has the potential to optimize the operational efficiency of distributed energy systems. It can be achieved by leveraging the reserve capacity of these resources. The effective use of this reserved capacity results in enhanced planning, scheduling, and operation optimization. Forecasting the power consumption of EERs is an essential part of reserved capacity calculation. This research presents a review of machine learning (ML)-based techniques utilized for short-term power consumption forecasting for a category of EERs specifically identified as thermostatically controlled loads (TCLs). Given the complicated characteristics and the difficulty in forecasting these resources, the existing research in this area is quite limited and there is still space for further studies. Moreover, this review underscores the importance of dedicating resources to further research, including developing replicable case studies and exploring novel technologies in this field.

Current string matching methods often struggle to understand the true meaning of text due to their reliance on simple character comparisons.Advancements in AI, particularly machine learning, offer more flexible models that can grasp the underlying meaning of words and phrases.This analysis explores various AI techniques for string matching, including neural networks, graph models, and attention mechanisms.These approaches aim to identify hidden features within text to achieve more accurate matching, even when dealing with real-world variations, errors, and unclear language.However, challenges remain in terms of processing speed, understanding how the models reach their conclusions, and adapting them to different applications.This review highlights areas for future research to improve AIpowered string matching, leveraging recent developments in statistical learning to create more reliable and scalable solutions for a wide range of fields.

Food safety is being transformed by artificial intelligence (AI), which is boosting contamination detection, real time monitoring and transparency of food supply chain. AI based techniques like machine learning, deep learning and computer vision help to detect chemical, microbial and physical contaminants in food more accurately and efficiently. These advancements have led processes to be automated, minimize the impact of human error and facilitate better decision taking. Other innovations include rapid, automated detection and traceability using AI driven spectroscopy, sensor based monitoring and block chain integration. Challenges in adopting AI, however, include fragmented and proprietary data, lack of model interpretability, the sheer implementation costs, and regulatory hurdles. Implementing AI has cost and technical challenges for small and medium sized businesses. Also, the AI models must be explainable and FMV compliant to provide the necessary transparency and reliability. Future research will consist of building upon the AI models developed in this thesis, incorporation of AI with IoT and edge computing for real time monitoring as well as setting up of ethical and regulatory frameworks. Trust in AI driven food safety will be developed with standardized AI regulations, unbiased predictions, and data privacy protections. Although AI presents some hurdles, it has the power to contribute in building a much safer, more efficient and transparent global food supply chain.

Thermoelectric (TE) materials have garnered significant interest due to their capacity to convert heat directly into electrical energy and vice versa, offering a sustainable route for energy harvesting and waste heat recovery. Nevertheless, many of the high-performance TE materials reported to date rely on elements that are scarce, costly, or environmentally hazardous, thereby limiting their large-scale deployment. To overcome these challenges, the development of efficient, earth-abundant, and environmentally benign alternatives is essential. Although first-principles methods provide valuable insights into the transport behavior of potential TE materials, their high computational cost restricts their utility in large-scale material screening. Recent progress in computational infrastructure, along with the advent of data-centric approaches such as machine learning (ML), has transformed the landscape of thermoelectric research. ML algorithms, trained on comprehensive datasets including experimental measurements, crystallographic data, and density functional theory (DFT) results can predict key TE metrics, such as the figure of merit (ZT), with remarkable speed and accuracy. This review explores the integration of ML into TE materials discovery, emphasizing its role in property prediction, descriptor engineering, and structural optimization. A systematic examination of ML-driven strategies promises to accelerate the discovery process and improve the efficiency of next-generation thermoelectric systems.

This review paper explores recent advances in machine learning approaches with emphasis on deep learning techniques for non-invasive cognitive impairment detection. We examine various non-invasive indicators of cognitive decline, including speech and language, facial, and motoric mobility. The paper provides an overview of relevant datasets, feature-extracting techniques, and deep-learning architectures applied to this domain. The paper comprises 60 peer-reviewed papers that mainly utilize deep learning models to detect cognitive impairment conditions. We have analyzed the performance of different methods across modalities and observed that speech and language-based methods generally achieved the highest detection performance. Studies combining acoustic and linguistic features tended to outperform those using a single modality. Facial analysis methods showed promise for visual modalities but were less extensively studied. Most papers focused on binary classification (impaired vs. non-impaired), with fewer addressing multi-class or regression tasks. Transfer learning and pre-trained language models emerged as popular and effective techniques, especially for linguistic analysis. Despite significant progress, several challenges remain, including data standardization and accessibility, model explainability, longitudinal analysis limitations, and clinical adaptation. Lastly, we propose future research directions, such as investigating language-agnostic speech analysis methods, developing multi-modal diagnostic systems, and addressing ethical considerations in AI-assisted healthcare. By synthesizing current trends and identifying key obstacles, this review aims to guide further development of deep learning-based cognitive impairment detection systems to improve early diagnosis and ultimately patient outcomes.