Carrots or sticks in debt collection services? A voice metrics and text analysis of debt collection calls

2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Chengcheng Liao ◽  
Peiyuan Du ◽  
Yutao Yang ◽  
Ziyao Huang
Keyword(s):  
Language Processing ◽  
Financial Services ◽  
Black Box ◽  
Content Type ◽  
Phone Calls ◽  
Behavioral Mechanism ◽  
Repeated Calls ◽  
Textual Data ◽  
Debt Collectors ◽  
Debt Collection

PurposeAlthough phone calls are widely used by debt collection services to persuade delinquent customers to repay, few financial services studies have analyzed the unstructured voice and text data to investigate how debt collection call strategies drive customers to repay. Moreover, extant research opens the “black box” mainly through psychological theories without hard behavioral data of customers. The purpose of our study is to address this research gap.Design/methodology/approachThe authors randomly sampled 3,204 debt collection calls from a large consumer finance company in East Asia. To rule out alternative explanations for the findings, such as consumers' previous experience of being persuaded by debt collectors or repeated calls, the authors selected calls made to delinquent customers who had not been delinquent before and were being called by the company for the first time. The authors transformed the unstructured voice and textual data into structured data through automatic speech recognition (ASR), voice mining, natural language processing (NLP) and machine learning analyses.FindingsThe findings revealed that (1) both moral appeal (carrot) and social warning (stick) strategies decrease repayment time because they arouse mainly happy emotion and fear emotion, respectively; (2) the legal warning (stick) strategy backfires because of decreasing the happy emotion and triggering the anger emotion, which impedes customers' compliance; and (3) in contrast to traditional wisdom, the combination of carrot and stick fails to decrease the repayment time.Originality/valueThe findings provide a valuable and systematic understanding of the effect of carrot strategies, stick strategies and the combinations of them on repayment time. This study is among the first to empirically analyze the effectiveness of carrot strategies, stick strategies and their joint strategies on repayment time through unstructured vocal and textual data analysis. What's more, the previous studies open the “black box” through psychological mechanism. The authors firstly elucidate a behavioral mechanism for why consumers behave differently under varying debt collection strategies by utilizing ASR, NLP and vocal emotion analyses.

Estimating numerical scale ratings from text-based service reviews

2020 ◽  
Vol 31 (2) ◽  
pp. 187-202
Author(s):  
Hsiu-Yuan Tsao ◽  
Ming-Yi Chen ◽  
Colin Campbell ◽  
Sean Sands
Keyword(s):  
Language Processing ◽  
Text Analysis ◽  
Design Methodology ◽  
Survey Methods ◽  
Content Type ◽  
Consumer Review ◽  
Numerical Scale ◽  
Analysis Technique ◽  
Textual Data ◽  
Practical Implications

PurposeThis paper develops a generalizable, machine-learning-based method for measuring established marketing constructs using passive analysis of consumer-generated textual data from service reviews. The method is demonstrated using topic and sentiment analysis along dimensions of an existing scale: lodging quality index (LQI).Design/methodology/approachThe method induces numerical scale ratings from text-based data such as consumer reviews. This is accomplished by automatically developing a dictionary from words within a set of existing scale items, rather a more manual process. This dictionary is used to analyze textual consumer review data, inducing topic and sentiment along various dimensions. Data produced is equivalent with Likert scores.FindingsPaired t-tests reveal that the text analysis technique the authors develop produces data that is equivalent to Likert data from the same individual. Results from the authors’ second study apply the method to real-world consumer hotel reviews.Practical implicationsResults demonstrate a novel means of using natural language processing in a way to complement or replace traditional survey methods. The approach the authors outline unlocks the ability to rapidly and efficiently analyze text in terms of any existing scale without the need to first manually develop a dictionary.Originality/valueThe technique makes a methodological contribution by outlining a new means of generating scale-equivalent data from text alone. The method has the potential to both unlock entirely new sources of data and potentially change how service satisfaction is assessed and opens the door for analysis of text in terms of a wider range of constructs.

Topic features for machine learning-based sentiment analysis in Indonesian tweets

2019 ◽  
Vol 12 (1) ◽  
pp. 70-81 ◽  
Author(s):  
Hendri Murfi ◽  
Furida Lusi Siagian ◽  
Yudi Satria
Keyword(s):  
Machine Learning ◽  
Sentiment Analysis ◽  
Language Processing ◽  
Analysis Data ◽  
Data Representation ◽  
Support Vector ◽  
Data Sets ◽  
Content Type ◽  
Textual Data ◽  
Standard Word

Purpose The purpose of this paper is to analyze topics as alternative features for sentiment analysis in Indonesian tweets. Design/methodology/approach Given Indonesian tweets, the processes of sentiment analysis start by extracting features from the tweets. The features are words or topics. The authors use non-negative matrix factorization to extract the topics and apply a support vector machine to classify the tweets into its sentiment class. Findings The authors analyze the accuracy using the two-class and three-class sentiment analysis data sets. Both data sets are about sentiments of candidates for Indonesian presidential election. The experiments show that the standard word features give better accuracies than the topics features for the two-class sentiment analysis. Moreover, the topic features can slightly improve the accuracy of the standard word features. The topic features can also improve the accuracy of the standard word features for the three-class sentiment analysis. Originality/value The standard textual data representation for sentiment analysis using machine learning is bag of word and its extensions mainly created by natural language processing. This paper applies topics as novel features for the machine learning-based sentiment analysis in Indonesian tweets.

scholarly journals Debt Collection Violations in Financial Technology in a Cyber-ethic and Legal Perspective

2021 ◽  
Vol 6 (1) ◽  
pp. 13-21
Author(s):  
Wawan Edi Prastiyo ◽  
I Dewa Made Suartha
Keyword(s):  
Financial Services ◽  
Personal Data ◽  
Literature Study ◽  
Business World ◽  
Legal Perspective ◽  
Debt Collectors ◽  
Psychological Pressure ◽  
Debt Collection ◽  
The One ◽  
Financial Technology

The presence of financial technology (Fintech) on the one hand makes it easy for people to obtain credit, while on the other hand, it creates various problems. In this study, two issues will be discussed, namely the application of cyber-ethic in protecting personal data and legal issues in collecting debt on Fintech. This research is a qualitative research. Data in the study were collected by means of literature study and presented descriptively and analytically. Cyber-ethic is implemented by protecting personal data. It is a transformation of traditional ethics in cyberspace. The cyber-ethic is very necessary in the business world. The application of cyber-ethic in the world of Fintech is carried out by protecting the personal data of both borrowers and third parties. Cyber-ethic violations have implications for breaking the law. Some of the billing violations on the Fintech business are sexual harassment, defamation, threats and stalking. Borrowing customers are powerless to face debt collectors’ behavior, because the debt collectors use the borrowers’ personal data to exert psychological pressure on the debtors to pay according to the bills determined unilaterally by Fintech. This condition usually occurs in illegal Fintechs that are not registered with the Financial Services Authority.

Subjective and objective financial literacy, opinion leadership, and the use of retail banking services

2018 ◽  
Vol 36 (4) ◽  
pp. 784-804 ◽  
Author(s):  
Mohammad G. Nejad ◽  
Katayon Javid
Keyword(s):  
Financial Literacy ◽  
Financial Services ◽  
Conceptual Development ◽  
Retail Banking ◽  
Opinion Leadership ◽  
Content Type ◽  
Financial Decisions ◽  
Phone Calls ◽  
The Usa ◽  
Customer Services

Purpose The purpose of this paper is to explore the relationship between consumers’ subjective and objective financial literacy (OFL) – the necessary knowledge and skills to make effective personal financial decisions – and their effects on opinion leadership and the use of retail financial services. Design/methodology/approach In total, 486 US participants were surveyed. The demographical profile of the sample roughly resembled that of the USA population. Findings On average, consumers with moderate levels of OFL report lower subjective financial literacy (SFL) compared to those with low or high levels of OFL. Moreover, while SFL and opinion leadership are positively correlated, consumers with moderate levels of OFL reported lower opinion leadership compared to those with high or low levels of OFL. The paper introduces financial literacy miscalibration as the discrepancy between consumers’ objective and SFL. Financially illiterate respondents who perceived themselves as financially knowledgeable reported high opinion leadership. Finally, a greater percentage of financially – literate consumers reported owning checking and savings accounts, using online and mobile banking for diverse purposes, and making fewer phone calls to customer services, compared to others. Research limitations/implications The paper integrates literature from financial literacy, consumer knowledge, and opinion leadership to explain these findings and to further enhance our theoretical and empirical understanding of objective vs SFL. Practical implications The discrepancies between objective and SFL may significantly influence consumers’ financial decisions and the degree to which they expose themselves to the pertinent risks. The paper discusses implications for public policy makers as well as marketing managers and researchers. Originality/value The study is the first to empirically explore the research questions following the conceptual development.

Assessing business process complexity based on textual data: Evidence from ITIL IT ticket processing

2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Nina Rizun ◽  
Aleksandra Revina ◽  
Vera G. Meister
Keyword(s):  
Information Technology ◽  
Language Processing ◽  
Business Process ◽  
Real World ◽  
Content Type ◽  
Real World Application ◽  
Starting Point ◽  
Two Samples ◽  
Textual Data ◽  
Cognitive Attention

PurposeThis study aims to draw the attention of business process management (BPM) research and practice to the textual data generated in the processes and the potential of meaningful insights extraction. The authors apply standard natural language processing (NLP) approaches to gain valuable knowledge in the form of business process (BP) complexity concept suggested in the study. It is built on the objective, subjective and meta-knowledge extracted from the BP textual data and encompassing semantics, syntax and stylistics. As a result, the authors aim to create awareness about cognitive, attention and reading efforts forming the textual data-based BP complexity. The concept serves as a basis for the development of various decision-support solutions for BP workers.Design/methodology/approachThe starting point is an investigation of the complexity concept in the BPM literature to develop an understanding of the related complexity research and to put the textual data-based BP complexity in its context. Afterward, utilizing the linguistic foundations and the theory of situation awareness (SA), the concept is empirically developed and evaluated in a real-world application case using qualitative interview-based and quantitative data-based methods.FindingsIn the practical, real-world application, the authors confirmed that BP textual data could be used to predict BP complexity from the semantic, syntactic and stylistic viewpoints. The authors were able to prove the value of this knowledge about the BP complexity formed based on the (1) professional contextual experience of the BP worker enriched by the awareness of cognitive efforts required for BP execution (objective knowledge), (2) business emotions enriched by attention efforts (subjective knowledge) and (3) quality of the text, i.e. professionalism, expertise and stress level of the text author, enriched by reading efforts (meta-knowledge). In particular, the BP complexity concept has been applied to an industrial example of Information Technology Infrastructure Library (ITIL) change management (CHM) Information Technology (IT) ticket processing. The authors used IT ticket texts from two samples of 28,157 and 4,625 tickets as the basis for the analysis. The authors evaluated the concept with the help of manually labeled tickets and a rule-based approach using historical ticket execution data. Having a recommendation character, the results showed to be useful in creating awareness regarding cognitive, attention and reading efforts for ITIL CHM BP workers coordinating the IT ticket processing.Originality/valueWhile aiming to draw attention to those valuable insights inherent in BP textual data, the authors propose an unconventional approach to BP complexity definition through the lens of textual data. Hereby, the authors address the challenges specified by BPM researchers, i.e. focus on semantics in the development of vocabularies and organization- and sector-specific adaptation of standard NLP techniques.

scholarly journals Regulatory Arbitrage and Non-Judicial Debt Collection in Central and Eastern Europe - Tax Sheltering and Potential Money Laundering

2020 ◽  
Vol 0 (0) ◽  
Author(s):  
Catalin-Gabriel Stanescu ◽  
Camelia Bogdan
Keyword(s):  
Eastern Europe ◽  
Money Laundering ◽  
Central And Eastern Europe ◽  
Regulatory Arbitrage ◽  
Legal Provisions ◽  
Regulatory Standards ◽  
Debt Collectors ◽  
Illegal Activities ◽  
Collection Practices ◽  
Debt Collection

AbstractNon-judicial recovery of debts is now rampant in Central and Eastern Europe (CEE). The reason is two-fold. On the one hand, the significant number of defaults in the poorer areas of Europe makes the CEE region a very attractive market for debt-collection. On the other hand, the activity is almost entirely unregulated, especially regarding abusive debt collection practices. The CEE region still lacks mature, strong, and experienced supervisory agencies that could tackle borderline activities. This enables companies involved in debt collection to comply easily with the minimal legal provisions and to circumvent the actual purpose of the law, including through tax sheltering and money laundering. The main argument developed in the paper is that the debt collection system it is designed to maximize profits, minimize tax base and, potentially, can serve as money laundering mechanism. The system functions in a triadic relationship: the debt-seller (a credit institution), the debt-buyer (usually an investment company), and the debt-administrator (a debt-collection agency, either fully owned by, or under the control of the debt-buyer), where debt portfolios are purchased at huge discounts (varying between 90 and 95% of face value). By revealing the mechanism used by debt-collectors, the paper calls for legislative intervention to seal the gap and ensure adequate taxation of debt-collection activities. The nature of regulatory arbitrage involved relates both to tax law as well as to regulatory standards, such as licensing requirements. Debt buyers benefit from the EU passport rule, make high returns on their 'investments' and optimize their taxes on profits obtained. Debt administrators perform their activity at almost no liability and no tax payable to the state. This mechanism creates favorable premises for money laundering and financing of illegal activities, as the web of offshore companies behind the debt-buyer renders the verification of the origin of their investment money extremely difficult. Using Romania as a case study, the paper addresses not only the aforementioned practices and risks, but also the potential reasons behind the state's inability either to adopt adequate legislation, or to enforce it. In doing so, the paper employs empirical evidence regarding the activity of ten Romanian debt collection agencies and relevant case law thereof. The paper concludes with the authors' proposal for a potential solution, which can be extended beyond Romania.

scholarly journals A Bilingual Comparison of Sentiment and Topics for a Product Event on Twitter

2021 ◽  
Author(s):  
Irina Wedel ◽  
Michael Palk ◽  
Stefan Voß
Keyword(s):  
Social Media ◽  
Language Processing ◽  
Topic Modeling ◽  
New Product ◽  
Business Value ◽  
Data Driven ◽  
New Product Introduction ◽  
Social Media Analytics ◽  
Product Introduction ◽  
Textual Data

AbstractSocial media enable companies to assess consumers’ opinions, complaints and needs. The systematic and data-driven analysis of social media to generate business value is summarized under the term Social Media Analytics which includes statistical, network-based and language-based approaches. We focus on textual data and investigate which conversation topics arise during the time of a new product introduction on Twitter and how the overall sentiment is during and after the event. The analysis via Natural Language Processing tools is conducted in two languages and four different countries, such that cultural differences in the tonality and customer needs can be identified for the product. Different methods of sentiment analysis and topic modeling are compared to identify the usability in social media and in the respective languages English and German. Furthermore, we illustrate the importance of preprocessing steps when applying these methods and identify relevant product insights.

scholarly journals Machine Learning for Dissimulating Reality

Proceedings ◽  
2021 ◽  
Vol 77 (1) ◽  
pp. 17
Author(s):  
Andrea Giussani
Keyword(s):  
Machine Learning ◽  
Language Processing ◽  
Huge Amount ◽  
Generative Adversarial Network ◽  
Adversarial Network ◽  
Technological Advances ◽  
Textual Data ◽  
Musical Scores ◽  
Mathematical Formulas

In the last decade, advances in statistical modeling and computer science have boosted the production of machine-produced contents in different fields: from language to image generation, the quality of the generated outputs is remarkably high, sometimes better than those produced by a human being. Modern technological advances such as OpenAI’s GPT-2 (and recently GPT-3) permit automated systems to dramatically alter reality with synthetic outputs so that humans are not able to distinguish the real copy from its counteracts. An example is given by an article entirely written by GPT-2, but many other examples exist. In the field of computer vision, Nvidia’s Generative Adversarial Network, commonly known as StyleGAN (Karras et al. 2018), has become the de facto reference point for the production of a huge amount of fake human face portraits; additionally, recent algorithms were developed to create both musical scores and mathematical formulas. This presentation aims to stimulate participants on the state-of-the-art results in this field: we will cover both GANs and language modeling with recent applications. The novelty here is that we apply a transformer-based machine learning technique, namely RoBerta (Liu et al. 2019), to the detection of human-produced versus machine-produced text concerning fake news detection. RoBerta is a recent algorithm that is based on the well-known Bidirectional Encoder Representations from Transformers algorithm, known as BERT (Devlin et al. 2018); this is a bi-directional transformer used for natural language processing developed by Google and pre-trained over a huge amount of unlabeled textual data to learn embeddings. We will then use these representations as an input of our classifier to detect real vs. machine-produced text. The application is demonstrated in the presentation.

Perceptions of time at work

2016 ◽  
Vol 45 (1) ◽  
pp. 29-50 ◽  
Author(s):  
Aristides Isidoro Ferreira ◽  
Joana Diniz Esteves
Keyword(s):  
Gender Differences ◽  
Design Methodology ◽  
Internet Use ◽  
The Internet ◽  
Content Type ◽  
Future Studies ◽  
Work Related ◽  
Phone Calls ◽  
Working Day ◽  
The Relationship

Purpose – Activities such as making personal phone calls, surfing on the internet, booking personal appointments or chatting with colleagues may or may not deviate attentions from work. With this in mind, the purpose of this paper is to examine gender differences and motivations behind personal activities employees do at work, as well as individuals’ perception of the time they spend doing these activities. Design/methodology/approach – Data were obtained from 35 individuals (M age=37.06 years; SD=7.80) from a Portuguese information technology company through an ethnographic method including a five-day non-participant direct observation (n=175 observations) and a questionnaire with open-ended questions. Findings – Results revealed that during a five-working-day period of eight hours per day, individuals spent around 58 minutes doing personal activities. During this time, individuals engaged mainly in socializing through conversation, internet use, smoking and taking coffee breaks. Results revealed that employees did not perceive the time they spent on non-work realted activities accurately, as the values of these perceptions were lower than the actual time. Moreover, through HLM, the findings showed that the time spent on conversation and internet use was moderated by the relationship between gender and the leisure vs home-related motivations associated with each personal activity developed at work. Originality/value – This study contributes to the literature on human resource management because it reveals how employees often perceive the time they spend on non-work related activities performed at work inaccurately. This study highlights the importance of including individual motivations when studying gender differences and personal activities performed at work. The current research discusses implications for practitioners and outlines suggestions for future studies.

The behavior of managers handling digital business transformations: theoretical issues and preliminary evidence from firms in the manufacturing industry

2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Diego Matricano ◽  
Laura Castaldi ◽  
Mario Sorrentino ◽  
Elena Candelo
Keyword(s):  
Organizational Culture ◽  
Case Studies ◽  
Manufacturing Industry ◽  
Qualitative Content Analysis ◽  
Preliminary Evidence ◽  
Digital Innovation ◽  
Content Type ◽  
Textual Data ◽  
Before And After ◽  
Theoretical Issues

PurposeOrganizational culture plays a central role when dealing with the issue of digital business transformation (DBT). Managers handling a DBT and involved in digital strateging are expected to modify the organizational culture of firms to make it more fitting with the paradigm of digital economy and having more chance of success. Thus, it is noteworthy to inspect the role they can have over DBTs. Accordingly, the purpose of this paper is to investigate the behavior that managers assume when they approach DBTs by investigating whether they act as mentors/facilitators or entrepreneurs/innovators, as coordinators or decision makers.Design/methodology/approachTo achieve the above purpose, ten case studies about manufacturing firms have been selected. Case studies, retrieved by the Digital Innovation Observatories of the School of Management of the Politecnico di Milano, are studied and analyzed by means of a qualitative content analysis on textual data. This allows getting specific insights into organizational culture before and after DBT and about the role played by managers.FindingsAchieved results disclose that managers need to modify the organizational culture of their firms to handle a successful DBT. However, firms can assume different organizational culture and thus the role assumed by managers handling a DBT can change as well.Originality/valueTo the authors knowledge, this paper is among the first that aim to investigate the role that mangers assume when handling DBTs. In particular, originality lies in the fact that assumed roles are rebuilt in reference to their ability to modify organizational culture.

Sign in / Sign up

Export Citation Format

Share Document