Consumption Behavior Analysis of Over the Top Services: Incremental Learning or Traditional Methods?

Rojas, Juan Sebastián; Gallón, Álvaro Rendón; Corrales, Juan Carlos

doi:10.1109/access.2019.2942782

Cited by 19 publications

(17 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The dataset was acquired from kaggle and was collected in a network section from Universidad Del Cauca, Popayán, Colombia spanning 6 days with different times between the months of April and May 2017 44 . CICFlowMeter is used to capture these TCP and UDP network flows; labels are assigned utilizing DPI with ntopng 45 .…”

Section: Methodsmentioning

confidence: 99%

Application layer classification of Internet traffic using ensemble learning models

2020

View full text Add to dashboard Cite

Summary Accurate application layer classification of Internet traffic has been a necessary requirement for various regulatory, control, and operational purposes of Internet service provider (ISP). Due to the dynamic and ever evolving nature of Internet applications generating a diverse mixture of Internet traffic, it has been necessary to apply deep packet inspection (DPI) techniques for traffic classification. DPI methods offer accuracy but degrade overall network throughput and thus cause problems in ensuring quality of service (QoS) and maintaining service‐level agreements. Moreover, Internet traffic is mostly end to end encrypted. This in turn limits the applicability of DPI techniques and renders them useless, unless the encryption tunnel is broken by the service provider which would risk violating user privacy. To address these trade‐offs between classification accuracy, performance, and user privacy, we resort to machine learning (ML)‐based algorithms. In this article, we apply three ensemble ML algorithms and report their performance metrics in the application layer classification of Internet traffic.

show abstract

Section: Methodsmentioning

confidence: 99%

Application layer classification of Internet traffic using ensemble learning models

2020

View full text Add to dashboard Cite

show abstract

“…To address these challenges, carriers offer a variety of service contracts. Normally, if allocated bandwidth is exceeded, a service degradation is often applied [11]. This allows telecommunication carriers to better manage large and complex network resources.…”

Section: Motivation and Objectivementioning

confidence: 99%

“…Rojas et al proposed a method of classifying users based on OTT usage data [11,12,45]. They used various ML methods to analyze OTT traffic and classified consumers into three consumption categories: high, medium, and low.…”

Section: Review Of Classification Using MLmentioning

confidence: 99%

A Heterogeneous Learning Framework for Over-the-Top Consumer Analysis Reflecting the Actual Market Environment

Choi

Kim

2021

Applied Sciences

View full text Add to dashboard Cite

The over-the-top (OTT) market for media consumption over wired and wireless Internet is growing. It is, therefore, crucial that service providers and carriers participating in the OTT market analyze consumer traffic for pricing, service delivery, infrastructure investments, etc. The OTT market has many consumer groups, but the proportion of users is not consistent in each. Furthermore, as multimedia consumption has increased owing to the COVID-19 epidemic, the OTT market has changed rapidly. If this is not reflected, the analysis will not be accurate. Therefore, we propose a framework that can classify consumers well based on actual OTT market environment conditions. First, by applying our proposed conditional probability-based method to basic machine learning techniques, such as support vector machine, k-nearest neighbor, and decision tree, we can improve the classification performance, even for an imbalanced OTT consumer distribution. Then, it is possible to analyze the changing consumer trends by dynamically retraining the incoming OTT consumer data. Conventional methods result in low classification accuracy in low-number classes, but our method shows an improvement of 5.3–19.2% based on recall. Moreover, conventional methods have shown large fluctuations in performance as the OTT market environment has changed, but our framework consistently maintains high performance.

show abstract

“…First, the input user behavior data need to be processed by interruption correction, which uses (8) or (9) to eliminate the discontinuous records. Then the parameter estimation and time window optimization are realized by (7) within the interest formation period to build the personalized user interest model, based on which the behavioral prediction is finally achieved by (6).…”

Section: Improved Semr Model With Interruption Correctionmentioning

confidence: 99%

“…At first, we divide users into three groups according to their viewing trend: UP (indicates the users whose behavioral indexes show a general upward trend), DOWN (indicates the users whose behavioral indexes show a general downward trend), and STEADY (indicates the users whose behavioral indexes are generally stable). We then estimate parameters c, k, h, and d using the least square method (7) and plot the corresponding retention and enhancement curves in Fig. 8.…”

Section: Extended Experiments a User Behavior Tendency Analysismentioning

confidence: 99%

Step-Enhancement of Memory Retention for User Interest Prediction

Yin

et al. 2020

IEEE Access

View full text Add to dashboard Cite

User behavior modeling and interest prediction are always the key elements in preference analysis, product recommendation and personalized service. The psychological memory theory has been proved capable of reflecting changes in user interest. However, merely focusing on the memory forgetting mechanism (the retention-only model) or considering the superimposition of interest retention in short term (the gradual-retention model), existing methods have a poor prediction capability because of ignoring the long-term impact of repeated behaviors. In this paper, we propose a step-enhancement of memory retention (SEMR) model which integrates the cross-enhancement-effects of multiple historical behaviors under different time windows to characterize user interest. In addition, we use some extended correction methods to eliminate the effect of discontinuous records. Numerical experiments using real TV viewing data validate the efficiency of our proposed model and methods, which reduce the average prediction error to 0.3, outperforming the traditional models by around 50%.

show abstract

Consumption Behavior Analysis of Over the Top Services: Incremental Learning or Traditional Methods?

Cited by 19 publications

References 18 publications

Application layer classification of Internet traffic using ensemble learning models

Application layer classification of Internet traffic using ensemble learning models

A Heterogeneous Learning Framework for Over-the-Top Consumer Analysis Reflecting the Actual Market Environment

Step-Enhancement of Memory Retention for User Interest Prediction

Contact Info

Product

Resources

About