Support Tickets Research Articles

Preprocessing Text Data for the Doc2Vec Model in the Automatic Classification of Tickets in Support Centers of Software Providers

Leading software providers typically implement customer technical support functions, which are crucial for promoting and enhancing the competitiveness of their products and services in global markets. The high volume and heterogeneity of support tickets (functional, temporal, linguistic, etc.) highlight the importance of efficient classification systems. Effective classification optimizes the distribution of these tickets among support center specialists and automates their processing using an established knowledge base. However, classifying these tickets is a loosely formalized task. For companies that have accumulated substantial data on customer requests, automating classification through machine learning methods and natural language processing models, such as Word2Vec, FastText, BERT, and GPT, becomes feasible. It is generally accepted that classification effectiveness primarily depends on the model employed. Nevertheless, the quality of these models is significantly influenced by the nature of the training data. Literature review of the reveals significant research interest in methods for the automatic classification of tickets specifically tailored to the operational conditions of software provider support centers. However, there is a noticeable gap in the literature regarding the impact of data preprocessing on the quality of these models. The article aims to clarify the techniques of data preprocessing and analyze their impact on the effectiveness of text classification, considering the specificity of software provider support centers. This study examines the stages of the automatic classification process for tickets, accounting for the unique characteristics of the data (customer text requests). A relevant set of specified methodological and instrumental tools was developed and tested using open data from a global software provider (DevExpress). The testing involved a database of 165,000 tickets. The study's results indicate that preprocessing can improve classification metrics such as F-measure, Precision, and Recall from 77% to 79%. Additionally, preprocessing significantly reduces the dimensionality of text data (by 48.2%) and increases model training speed (by 26.5%) without loss of accuracy, ensuring cost-efficiency and operational efficiency in the use of computational resources.

Performance Evaluation on Resolution Time Prediction Using Machine Learning Techniques

The quality of customer service emphasizes support tickets. An excellent support ticket system qualifies businesses to provide clients with the finest level of customer support. This enables enterprises to guarantee the consistency of quality customer service delivered successfully, ensuring all clients have a good experience regardless of the nature of their inquiry or issue. To further achieve a higher efficiency of resource allocation, this is when the prediction of ticket resolution time comes into place. The advancing technologies, including artificial intelligence (AI) and machine learning (ML), can perform predictions on the duration required to tackle specific problems based on past similar data. ML enables the possibility of automatically classifying tickets, making it possible to anticipate the time resolution for cases. This paper explores various ML techniques widely applied in the Resolution Time Prediction system and investigates the performance of three selected ML techniques via the benchmarking dataset obtained from the UCI Machine Learning Repository. Implementing selected techniques will involve creating a graphical user interface and data visualization to provide insight for data analysis. The best technique will be concluded after performing the ML technique evaluation. The evaluation metrics involved in this step include Root Mean Square Error (RMSE) and Root Mean Absolute Error (MAE). The experimental evaluation shows that the best performance among the selected ML techniques is Random Forest (RF).

The Role of Value Co-Creation Towards Non-financial Performances: Mediating Effect of Customer Support Ticket in the Context of Life Insurance Sector in Sri Lanka

Nowadays, value co-creation plays a vital role in acquiring new business and retaining customers in the competitive business world. Understanding customers and providing them with personalized experiences has become a trend. Value co-creation also plays a crucial role in brand development, as it contributes to brand equity, reputation, and credibility. These factors guide consumer decisions, determining whether they become loyal to a brand or switch to another. Despite its importance, the specific mechanisms through which value co-creation impacts non-financial performances in the life insurance sector in Sri Lanka have not been thoroughly explored. Therefore, the main purpose of this research is to study the impact of value co-creation on the non-financial performances of life insurance policies in Sri Lanka. Dimensions of value co-creation, such as relational orientation, customer involvement, freedom of co-creation, and degree of collaboration, will be examined, along with the mediating effect of customer support tickets. A quantitative research strategy will be employed, utilizing data collected through surveys. The researcher has developed a scale based on previous literature to measure value co-creation and non-financial performances. Reliability and validity of the scales were tested using survey data. The study was conducted in a descriptive manner, allowing for natural settings and avoiding researcher interference. Primary data were collected from a convenient sample of 142 employees working in life top performing insurance companies residing in the Western Province. Regression and multiple regression analyses were conducted to examine the relationships. The results revealed that all elements of value co-creation significantly impact the non-financial performances of life insurance policies, and the moderator and mediator effects supported the framework. Finally, the researcher presented several recommendations for marketing strategies based on the study's results. This research contributes to the existing literature and fills the practice gap, providing avenues for future researchers to explore potential areas. Overall, this study emphasizes the importance of value co-creation in the life insurance sector, highlights its impact on non-financial performances, and offers valuable insights for marketing strategies in Sri Lanka.

A Value Co-Creation Perspective on Data Labeling in Hybrid Intelligence Systems: A Design Study

The adoption of innovative technologies confronts IT-Service-Management (ITSM) with an increasing volume and variety of requests. Artificial intelligence (AI) possesses the potential to augment customer service employees. However, the training data for AI systems are annotated by domain experts with little interest in labeling correctly due to their limited perceived value. Ultimately, insufficient labeled data leads to diminishing returns in AI performance. Following a design science research approach, we provide a novel human-in-the-loop (HIL) design for ITSM support ticket recommendations by incorporating a value co-creation perspective. The design incentivizes ITSM agents to provide labels during their everyday ticket-handling procedures. We develop a functional prototype based on 17,120 support tickets provided by a pilot partner as an instantiation and evaluate the design through accuracy metrics and user evaluations. Our evaluation revealed that recommendations after label improvement showed increased user ratings, and users are willing to contribute their domain knowledge. We demonstrate that our design benefits for both human agent and AI systems in the form of hybrid intelligence service systems. Overall, our results emphasize agents' need for value-in-use by providing better results if they improve the labeling of support tickets pre-labeled by AI. Thus, we provide prescriptive knowledge of a novel HIL design that enables efficient and interactive labeling in the context of diverse applications of reinforcement learning systems.

Improving IT Support Efficiency Using AI-Driven Ticket Random Forest Classification Technique

This research project aims to improve IT support efficiency at Indonesian company XYZ by using AI-based IT support ticket classification integration. This method involved collecting over 1,000 support tickets from the company's IT ticketing system, GLPI, and pre-processing the data to ensure the quality and relevance of the data for analysis. Claims data is enriched with relevant features, including textual information and categorical attributes such as urgency, impact, and requirement expertise. To improve the ticket preference matrix, AI-based language models, especially OpenAI's GPT-3, are used. These templates help to reclassify and improve the work of IT support teams. In addition, the ticket data is used to train the Random Forest classifier, allowing automatic classification of tickets based on their specific characteristics. The performance of the ticket classification system is evaluated using a variety of metrics, and the results are compared with alternative methods to assess effectiveness. of the Random Forest algorithm. This evaluation demonstrates the system's ability to correctly classify and prioritize incoming tickets. The successful implementation of this project at Company XYZ is a model for other organizations looking to optimize their IT support through AI-driven approaches. By providing simplified ticket classification and admission ticket reclassification based on AI algorithms, this research helps leverage AI technologies to improve IT support processes. Ultimately, the proposed solution benefits both support providers and users by improving efficiency, response times, and overall customer satisfaction.

The yea-paradox: Cognitive bias in technology acceptance surveys

Technology acceptance is widely regarded as one of the most established, mature, and continuously relevant streams of information systems research. Its fundamental assumption is that technology acceptance scores accurately reflect users’ intentions, needs, and emotions toward the technology of interest. However, many studies (including this one) present evidence that challenges this assumption, suggesting that the link between reported scores and actual perception is more complex than often assumed. We aim to find out how cognitive biases influence self-reported technology acceptance scores. We draw on dialogical iterations between an exploratory case study at Cloud Corp, a multinational Software-as-a-Service provider and related literature on technology acceptance and cognitive bias. Our study reveals a paradoxical relationship between reported acceptance scores and actual perceptions: Despite providing high acceptance scores, users did not actually use the technology. Conversely, users who complained a lot by filing many support tickets were more engaged with the technology When yea-saying users meet yea-hearing designers, technology acceptance scores may be spuriously inflated, providing an exaggerated picture of users’ attitudes toward a technology. We call this the ‘yea-paradox’ because of its roots in people's tendency to agree half-heartedly (‘yea’), even when they privately disagree, to avoid more complex and potentially difficult conversations.

Hyperparameter Black-Box Optimization to Improve the Automatic Classification of Support Tickets

User requests to a customer service, also known as tickets, are essentially short texts in natural language. They should be grouped by topic to be answered efficiently. The effectiveness increases if this semantic categorization becomes automatic. We pursue this goal by using text mining to extract the features from the tickets, and classification to perform the categorization. This is however a difficult multi-class problem, and the classification algorithm needs a suitable hyperparameter configuration to produce a practically useful categorization. As recently highlighted by several researchers, the selection of these hyperparameters is often the crucial aspect. Therefore, we propose to view the hyperparameter choice as a higher-level optimization problem where the hyperparameters are the decision variables and the objective is the predictive performance of the classifier. However, an explicit analytical model of this problem cannot be defined. Therefore, we propose to solve it as a black-box model by means of derivative-free optimization techniques. We conduct experiments on a relevant application: the categorization of the requests received by the Contact Center of the Italian National Statistics Institute (Istat). Results show that the proposed approach is able to effectively categorize the requests, and that its performance is increased by the proposed hyperparameter optimization.

Extracting Features from Textual Data in Class Imbalance Problems

We address class imbalance problems. These are classification problems where the target variable is binary, and one class dominates over the other. A central objective in these problems is to identify features that yield models with high precision/recall values, the standard yardsticks for assessing such models. Our features are extracted from the textual data inherent in such problems. We use n-gram frequencies as features and introduce a discrepancy score that measures the efficacy of an n-gram in highlighting the minority class. The frequency counts of n-grams with the highest discrepancy scores are used as features to construct models with the desired metrics. According to the best practices followed by the services industry, many customer support tickets will get audited and tagged as “contract-compliant” whereas some will be tagged as “over-delivered”. Based on in-field data, we use a random forest classifier and perform a randomized grid search over the model hyperparameters. The model scoring is performed using an scoring function. Our objective is to minimize the follow-up costs by optimizing the recall score while maintaining a base-level precision score. The final optimized model achieves an acceptable recall score while staying above the target precision. We validate our feature selection method by comparing our model with one constructed using frequency counts of n-grams chosen randomly. We propose extensions of our feature extraction method to general classification (binary and multi-class) and regression problems. The discrepancy score is one measure of dissimilarity of distributions and other (more general) measures that we formulate could potentially yield more effective models.

Classification of Support Tickets using Different Vectorization and Pre-Processing Methods

Firmalarda, ihtiyaçlara yönelik gelen taleplerin doğru şekilde işlenmesi hem iş sürecini hızlandırır hem de ortaya çıkabilecek sorunları bertaraf eder. Geliştirme, destek, sorun çözme gibi farklı konulardaki taleplerin, verimli ve doğru kişilerce çözülmesi için öncelikle ilgili alt departmana yönlendirilmesi gerekir. Yönlendirmeler belirli kişilerce elle gerçekleştirilebilir. Ancak firma büyüklüğüyle doğru orantılı olarak gelen talep sayısının çok olması süreci zorlaştırıp zaman kaybına yol açmaktadır. Özellikle bilişim sektöründe hizmet veren kurumsal firmalarda taleplerin otomatik olarak alt-departmanlara aktarılabilmesi, işin verimliliğinin ciddi şekilde arttırabilir. Bu ihtiyacın giderilmesi içi metni işleyerek içerisinden kolaylıkla bilgi çıkarımını sağlayabilen metin madenciliği ve makine öğrenmesi yöntemleri kullanılabilir. Çalışmamızda, Detaysoft Danışmanlık firmasına ait gelen taleplerin doğru şekilde alt departmana yönlendirilmesini sağlayan bir sistem önerilmiştir. Sistem performansının ölçülebilmesi amacıyla gerçek müşteri taleplerinden oluşan 2103 veri toplanmış ve işaretlenmiştir. Toplanan verilerin varsayımlardan bağımsız olarak doğru şekilde işaretlenmesi için de veriye göre sınıf etiketlerinin belirlendiği temellendirilmiş teoriden faydalanılmıştır. Ham metinlerin vektörleştirilmesi için kelime çantası ve türevlerinin (TF, TFIDF) yanı sıra GloVe ve Word2Vec gibi kelime gömme yöntemleri de denenmiş ve hangi vektörleştirme yönteminin daha başarılı olduğu irdelenmiştir. Ayrıca gereksiz kelimelerin ve sadece kelime köklerinin kullanılmasının talep sınıflandırmaya etkileri analiz edilmiştir. Yapılan analizler sonucunda SVM algoritmasını kullanan modellerin %79 gibi iyi sayılabilecek bir başarım ile gelen talebi doğru şekilde sınıflandırabildiği gözlemlenmiştir. Elde edilen sonuçların, talep sınıflandırma konularındaki gelecek çalışmalara hem vektörleştirme hem de ön işlem süreçleriyle alakalı ışık tutması beklenmektedir.

A multiapproach generalized framework for automated solution suggestion of support tickets

Nowadays, customer support systems are one of the key factors in maintaining any big company's reputation and success. These systems are capable of handling a large number of tickets systemically and provides a mechanism to track/logs the communication between customer and support agents. Companies invest huge amounts of money in training support agents and deploying customer care services for their products and services. Support agents are responsible for handling different customer queries and implementing required actions to solve a particular issue or problem raised by the service/product user. In a bigger picture, customer support systems could receive a large amount of ticket raised depending upon the number of users and services being offered. Customer care service gets directly affected due to the high volume of tickets and a limited number of support agents. Therefore, providing support agents with the recommendations about the possible resolution actions for a new ticket would be helpful and can save a lot of time. This study is focused on the development of an end-to-end framework for suggesting resolution actions rather than recommending free form resolution text against a newly raised ticket. To develop such a system, the pipeline is broadly divided into four components that are data preprocessing, actions extractor, resolution predictor, and evaluation. In actions extractor module, we have proposed a technique to identify and extract actionable phrases from resolution text. For resolution predictor, we have proposed two different pipelines that are referred as “Similarity Search Model” and “End-to-End Model.” The similarity search method is based on a ticket similarity search to find the most relevant historical tickets which then leads to corresponding resolution actions. On the other hand, end-to-end model make use of actions extractor module directly and implemented in a way to directly predict resolution actions. To compare and evaluate the mentioned methods on the same ground, we also proposed an actions evaluation criterion which uses BertScore and METEOR score jointly to compute the score against actual and predicted actions for a particular test ticket. The analysis and experiments are performed on the real-world IBM ticket data set. Overall, we observed that end-to-end model outperformed similarity search-based methods and achieved better performance and scores comparatively. The trained models and code are available at https://bit.ly/2GbUBVk.

Building ML Based Intelligent System to Analyze Production LSI Live Site Incidents

Providing support on the rolled-out application/services is one of the major factors in increasing the customer satisfaction which in turn increases the customer retention. Since we are in the era of automation where most of the day-to-day jobs are taken care of or are facilitated by the technologies around us, hence there is a need to reduce manual effort in triaging the support tickets and hence facilitating the person on call to better close the tickets on time with proper remediation. The machine learning model which will be the product of this complete paper will not only help in classifying the tickets but also, if applicable will give the best possible remediation of the ticket there by reducing the manual effort and the time taken on providing necessary solution on the ticket. The objectives of the work are as follows - a) Understand the data that is present in the ticket and figure out the basic understanding like, categories of issues, trends etc. b) Prepare the data which is ready for applying different classification algorithms. d) Identify the best machine learning model which can classify the new incident with utmost accuracy. e) Prepare a machine learning model which can suggest the best possible remediation of the ticket. f) Integrate the best classification model and solution recommender model and wrap it as an API which can be used by end user.

Analysis of Patterns and Similarities in Service Tickets using Natural Language Processing

In this paper we propose an approach for classifying documents, embedding documents into feature vectors and using these embeddings for finding similarities between them. Our chosen domain for applying this method is the IT-Service Support branch, where the documents we try to analyse are support tickets and the potential of classifying and finding patterns between tickets is huge for optimizing the service process. We aim to tackle the problem with multiple methods of text classification and recognition, and data analysis, followed by comparison and interpretation of the results. Following our previous work in this field, we propose further means of validating our models, so we can describe and visualize several methods of feature extraction and recognition for service tickets that help the business process for Service Support.

User behaviour analysis and churn prediction in ISP

There is no doubt that customer retention is vital for the service sector as companies’ revenue is significantly based on their customers’ financial returns. The prediction of customers who are at the risk of leaving a company’s services is not possible without using their connection details, support tickets and network traffic usage data. This paper demonstrates the importance of data mining and its outcome in the telecommunication area. The data in this paper are collected from different sources like Net Flow logs, call records and DNS query logs. These different types of data are aggregated together to decrease the missing information. Finally, machine learning algorithms are evaluated based on the customer dataset. The results of this study indicate that the gradient boosting algorithm performs better than other machine learning algorithms for this dataset.
 
 Keywords: Data analysis, customer satisfaction, subscriber churn, machine learning, telecommunication.

Author Correction: Customer support ticket escalation prediction using feature engineering

Understanding and keeping the customer happy is a central tenet of requirements engineering. Strategies to gather, analyze, and negotiate requirements are complemented by efforts to manage customer input after products have been deployed. For the latter, support tickets are key in allowing customers to submit their issues, bug reports, and feature requests. If insufficient attention is given to support issues, however, their escalation to management becomes time-consuming and expensive, especially for large organizations managing hundreds of customers and thousands of support tickets. Our work provides a step towards simplifying the job of support analysts and managers, particularly in predicting the risk of escalating support tickets. In a field study at our large industrial partner, IBM, we used a design science research methodology to characterize the support process and data available to IBM analysts in managing escalations. We then implemented these features into a machine learning model to predict support ticket escalations. We trained and evaluated our machine learning model on over 2.5 million support tickets and 10,000 escalations, obtaining a recall of 87.36% and an 88.23% reduction in the workload for support analysts looking to identify support tickets at risk of escalation. Finally, in addition to these research evaluation activities, we compared the performance of our support ticket model with that of a model developed with no feature engineering; the support ticket model features outperformed the non-engineered model. The artifacts created in this research are designed to serve as a starting place for organizations interested in predicting support ticket escalations, and for future researchers to build on to advance research in escalation prediction.

Customer support ticket escalation prediction using feature engineering

Understanding and keeping the customer happy is a central tenet of requirements engineering. Strategies to gather, analyze, and negotiate requirements are complemented by efforts to manage customer input after products have been deployed. For the latter, support tickets are key in allowing customers to submit their issues, bug reports, and feature requests. If insufficient attention is given to support issues, however, their escalation to management becomes time-consuming and expensive, especially for large organizations managing hundreds of customers and thousands of support tickets. Our work provides a step toward simplifying the job of support analysts and managers, particularly in predicting the risk of escalating support tickets. In a field study at our large industrial partner, IBM, we used a design science research methodology to characterize the support process and data available to IBM analysts in managing escalations. In a design science methodology, we used feature engineering to translate our understanding of support analysts' expert knowledge of their customers into features of a support ticket model. We then implemented these features into a machine learning model to predict support ticket escalations. We trained and evaluated our machine learning model on over 2.5 million support tickets and 10,000 escalations, obtaining a recall of 87.36% and an 88.23% reduction in the workload for support analysts looking to identify support tickets at risk of escalation. Further on-site evaluations, through a prototype tool we developed to implement our machine learning techniques in practice, showed more efficient weekly support ticket management meetings. Finally, in addition to these research evaluation activities, we compared the performance of our support ticket model with that of a model developed with no feature engineering; the support ticket model features outperformed the non-engineered model. The artifacts created in this research are designed to serve as a starting place for organizations interested in predicting support ticket escalations, and for future researchers to build on to advance research in escalation prediction.

Tracking the NGS revolution: managing life science research on shared high-performance computing clusters.

BackgroundNext-generation sequencing (NGS) has transformed the life sciences, and many research groups are newly dependent upon computer clusters to store and analyze large datasets. This creates challenges for e-infrastructures accustomed to hosting computationally mature research in other sciences. Using data gathered from our own clusters at UPPMAX computing center at Uppsala University, Sweden, where core hour usage of ∼800 NGS and ∼200 non-NGS projects is now similar, we compare and contrast the growth, administrative burden, and cluster usage of NGS projects with projects from other sciences.ResultsThe number of NGS projects has grown rapidly since 2010, with growth driven by entry of new research groups. Storage used by NGS projects has grown more rapidly since 2013 and is now limited by disk capacity. NGS users submit nearly twice as many support tickets per user, and 11 more tools are installed each month for NGS projects than for non-NGS projects. We developed usage and efficiency metrics and show that computing jobs for NGS projects use more RAM than non-NGS projects, are more variable in core usage, and rarely span multiple nodes. NGS jobs use booked resources less efficiently for a variety of reasons. Active monitoring can improve this somewhat.ConclusionsHosting NGS projects imposes a large administrative burden at UPPMAX due to large numbers of inexperienced users and diverse and rapidly evolving research areas. We provide a set of recommendations for e-infrastructures that host NGS research projects. We provide anonymized versions of our storage, job, and efficiency databases.

Advanced search system for IT support services

IBM's Technical Support Services division runs remote support centers, where agents provide phone support for client problems related to IBM and non-IBM hardware and software products. Support center personnel use numerous pieces of information—including many searches, log files, and records of historical support tickets, from disparate data sources—to recommend solutions for customer technical problems. We have built an advanced search system to assist support agents who are resolving customer service requests and improving our client experience. The system has been deployed and used globally by thousands of support center personnel. In this paper, we describe the system's architecture, the technical challenges, and the innovative solution we have built. In addition, we discuss the novel ideas to address the unique requirements and challenges of the support services domain. These ideas include using system logs and domain knowledge to automatically expand agent queries, incorporating implicit agent feedback, and selecting features to extract useful information from highly unstructured and noisy ticket data. Results on the effectiveness of the system are presented. We also discuss future work on enhancing the system's capability to automatically diagnose customer hardware and software problems and remediate them.

Understanding Post-Implementation Support for Enterprise Systems: An Empirical Study of IT Personnel's Customer-Oriented Citizenship Behaviors

ABSTRACTPost-implementation support for information systems (ISs) remains an important but under-explored topic. In this study, we focus on the customer service aspect of post-implementation support for enterprise resource planning (ERP) systems and examine the antecedents and performance consequences of customer-oriented organizational citizenship behaviors (OCBs) performed by information technology (IT) personnel. We predict that characteristics of IT support tasks influence IT personnel's customer-oriented OCBs, which in turn exert both direct and moderating effects on their task efficiency. The analysis of 300 support tickets in relation to two ERP modules (Supplier Relationship Management and HR/Payroll Management) in a large enterprise provides mixed results. Task type was found to be associated significantly with the occurrence of OCBs, but the influence of task complexity was not significant. Moreover, OCBs were found to be negatively related to task efficiency, but the degree of the negative relation was contingent on task type and task complexity. The findings enhance our understanding of IT support services and extend the OCB literature on customer orientation. Practically, the results offer insights into managing IT support and IT workforce during the post-implementation stage of information systems.

How Hadoop Clusters Break

This article describes an examination of a sample of several hundred support tickets for the Hadoop ecosystem, a widely used group of big data storage and processing systems; a taxonomy of errors and how they are addressed by supporters; and the misconfigurations that are the dominant cause of failures. Some design "antipatterns" and missing platform features contribute to these problems. Developers can use various methods to build more robust distributed systems, thereby helping users and administrators prevent some of these rough edges.