Learning Personalized Product Recommendations with Customer Disengagement

2021 ◽  
Author(s):  
Hamsa Bastani ◽  
Pavithra Harsha ◽  
Georgia Perakis ◽  
Divya Singhvi
Keyword(s):  
Learning Strategies ◽  
Salient Feature ◽  
Integer Program ◽  
Problem Definition ◽  
Customer Engagement ◽  
Simple Modification ◽  
Customer Preferences ◽  
Managerial Implications ◽  
Product Recommendations ◽  
Using Data

Problem definition: We study personalized product recommendations on platforms when customers have unknown preferences. Importantly, customers may disengage when offered poor recommendations. Academic/practical relevance: Online platforms often personalize product recommendations using bandit algorithms, which balance an exploration-exploitation trade-off. However, customer disengagement—a salient feature of platforms in practice—introduces a novel challenge because exploration may cause customers to abandon the platform. We propose a novel algorithm that constrains exploration to improve performance. Methodology: We present evidence of customer disengagement using data from a major airline’s ad campaign; this motivates our model of disengagement, where a customer may abandon the platform when offered irrelevant recommendations. We formulate the customer preference learning problem as a generalized linear bandit, with the notable difference that the customer’s horizon length is a function of past recommendations. Results: We prove that no algorithm can keep all customers engaged. Unfortunately, classical bandit algorithms provably overexplore, causing every customer to eventually disengage. Motivated by the structural properties of the optimal policy in a scalar instance of our problem, we propose modifying bandit learning strategies by constraining the action space up front using an integer program. We prove that this simple modification allows our algorithm to perform well by keeping a significant fraction of customers engaged. Managerial implications: Platforms should be careful to avoid overexploration when learning customer preferences if customers have a high propensity for disengagement. Numerical experiments on movie recommendations data demonstrate that our algorithm can significantly improve customer engagement.

Cause Marketing: Product Pricing, Design, and Distribution

2020 ◽  
Vol 22 (4) ◽  
pp. 775-791 ◽  
Author(s):  
Fei Gao
Keyword(s):  
Problem Definition ◽  
Cause Marketing ◽  
Pricing Decisions ◽  
Decentralized Supply Chain ◽  
Customer Preferences ◽  
Product Pricing ◽  
Analytical Work ◽  
Negative Effect ◽  
Managerial Implications ◽  
Social Cause

Problem definition: In a cause marketing (CM) campaign, a firm donates part of its sales revenue to a charity for a social cause when customers purchase the cause-linked product. We study a firm’s pricing decisions with CM and the implications for the participating charity. We also consider the design and distribution of cause-linked products. Academic/practical relevance: CM has become popular in recent years. However, there is little analytical work on how a firm’s strategic actions (e.g., product pricing, design, and distribution) impact the effectiveness of a CM campaign. We address this gap. Methodology: Game theory. Results: First, it may be optimal for the firm to decrease the price after the implementation of CM despite the donation cost. Second, a higher level of firm–cause fit may lead to a smaller total donation amount to the charity in a CM campaign. Third, the choice to design a special version of the product for a CM campaign depends on the size of the prosocial segment in the market. Fourth, a decentralized supply chain may generate more social value through CM compared with the centralized case. Managerial implications: For firms, we show that it may not be optimal to increase the price of cause-linked products and identify conditions where firms should introduce a special product in a CM campaign. For charities, we show that a high firm–cause fit level may have a negative effect on the total donation amount and further identify conditions under which charities should collaborate with a downstream retailer or an upstream manufacturer in a CM campaign. Our results indicate that the correlation between customer preferences for the product and the social cause has a significant impact in a CM campaign for both firms and charities.

On the Role of Teletriage in Healthcare Demand Management

2020 ◽  
Author(s):  
Özden Engin Çakıcı ◽  
Alex F. Mills
Keyword(s):  
Demand Management ◽  
Healthcare Providers ◽  
Health Condition ◽  
Acute Illness ◽  
Problem Definition ◽  
System Level ◽  
Illness Episode ◽  
Telemedicine Service ◽  
Managerial Implications ◽  
Using Data

Problem definition: Many healthcare providers and payers offer teletriage, a telemedicine service where concerned patients can get advice about their health condition. In theory, teletriage should help patients with an acute illness choose an appropriate provider, reducing unnecessary and duplicate provider visits, yet no study has assessed the overall costs and benefits of teletriage at a system level. Academic/practical relevance: We model the use of teletriage in managing healthcare demand and determine in which cases teletriage is efficient and effective. Our model extends the academic literature on service operations and provides practical suggestions for healthcare payers. Methodology: We use a Markov decision process to model a patient’s choices during an acute illness episode, where the illness severity is partially observable to the patient and triage is subject to errors. We parameterize the model using data from the literature and provide both structural and numerical results. Results: Patients with high uncertainty about their state would use the teletriage service, which may improve their cost outcomes. However, when teletriage is added, the rate of arrivals to the emergency department (ED) may increase when the overtriage rate is above 5%, the lowest value observed in the literature. Patient’s choices and the copayment of other services affect the cost-effectiveness of teletriage. Managerial implications: There are several reasons why adding teletriage to the healthcare system could produce a negative cost outcome. Teletriage should not necessarily be free, which would encourage use by patients with low levels of uncertainty and actually increase the payer’s total cost. The overtriage rate is a key driver of performance and must be managed carefully.

scholarly journals Budgeting in International Humanitarian Organizations

2021 ◽  
Author(s):  
Milad Keshvari Fard ◽  
Ivana Ljubić ◽  
Felix Papier
Keyword(s):  
Utility Function ◽  
Operations Management ◽  
Benders Decomposition ◽  
International Committee ◽  
Problem Definition ◽  
Red Cross ◽  
Solution Approach ◽  
Humanitarian Organizations ◽  
Managerial Implications ◽  
Using Data

Problem definition: International humanitarian organizations (IHOs) prepare a detailed annual allocation plan for operations that are conducted in the countries they serve. The annual plan is strongly affected by the available financial budget. The budget of IHOs is derived from donations, which are typically limited, uncertain, and to a large extent earmarked for specific countries or programs. These factors, together with the specific utility function of IHOs, render budgeting for IHOs a challenging managerial problem. In this paper, we develop an approach to optimize budget allocation plans for each country of operations. Academic/practical relevance: The current research provides a better understanding of the budgeting problem in IHOs given the increasing interest of the operations management community for nonprofit operations. Methodology: We model the problem as a two-stage stochastic optimization model with a concave utility function and identify a number of analytical properties for the problem. We develop an efficient generalized Benders decomposition algorithm as well as a fast heuristic. Results: Using data from the International Committee of the Red Cross, our results indicate 21.3% improvement in the IHO’s utility by adopting stochastic programming instead of the expected value solution. Moreover, our solution approach is computationally more efficient than other approaches. Managerial implications: Our analysis highlights the importance of nonearmarked donations for the overall performance of IHOs. We also find that putting pressure on IHOs to fulfill the targeted missions (e.g., by donors or media) results in lower beneficiaries’ welfare. Moreover, the IHOs benefit from negative correlation among donations. Finally, our findings indicate that, if donors allow the IHO to allocate unused earmarked donations to other delegations, the performance of the IHO improves significantly.

Partial Completion as a Nonprofit Strategy

2021 ◽  
Author(s):  
Can Zhang ◽  
Atalay Atasu ◽  
Karthik Ramachandran
Keyword(s):  
Nonprofit Organizations ◽  
Service Provision ◽  
Problem Definition ◽  
Product Service ◽  
Service Portfolio ◽  
Wide Range ◽  
Partial Completion ◽  
Innovative Solution ◽  
Managerial Implications ◽  
Level 3

Problem definition: Faced with the challenge of serving beneficiaries with heterogeneous needs and under budget constraints, some nonprofit organizations (NPOs) have adopted an innovative solution: providing partially complete products or services to beneficiaries. We seek to understand what drives an NPO’s choice of partial completion as a design strategy and how it interacts with the level of variety offered in the NPO’s product or service portfolio. Academic/practical relevance: Although partial product or service provision has been observed in the nonprofit operations, there is limited understanding of when it is an appropriate strategy—a void that we seek to fill in this paper. Methodology: We synthesize the practices of two NPOs operating in different contexts to develop a stylized analytical model to study an NPO’s product/service completion and variety choices. Results: We identify when and to what extent partial completion is optimal for an NPO. We also characterize a budget allocation structure for an NPO between product/service variety and completion. Our analysis sheds light on how beneficiary characteristics (e.g., heterogeneity of their needs, capability to self-complete) and NPO objectives (e.g., total-benefit maximization versus fairness) affect the optimal levels of variety and completion. Managerial implications: We provide three key observations. (1) Partial completion is not a compromise solution to budget limitations but can be an optimal strategy for NPOs under a wide range of circumstances, even in the presence of ample resources. (2) Partial provision is particularly valuable when beneficiary needs are highly heterogeneous, or beneficiaries have high self-completion capabilities. A higher self-completion capability generally implies a lower optimal completion level; however, it may lead to either a higher or a lower optimal variety level. (3) Although providing incomplete products may appear to burden beneficiaries, a lower completion level can be optimal when fairness is factored into an NPO’s objective or when beneficiary capabilities are more heterogeneous.

The Effects of Patent Extension and Take-Back Regulation on Green Pharmacy

2021 ◽  
Author(s):  
Tianqin Shi ◽  
Nicholas C. Petruzzi ◽  
Dilip Chhajed
Keyword(s):  
Pharmaceutical Industry ◽  
Social Welfare ◽  
Technical Information ◽  
Problem Definition ◽  
Theoretic Model ◽  
Innovative Company ◽  
Take Back ◽  
Starting Point ◽  
European Environmental Agency ◽  
Managerial Implications

Problem definition: The eco-toxicity arising from unused pharmaceuticals has regulators advocating the benign design concept of “green pharmacy,” but high research and development expenses can be prohibitive. We therefore examine the impacts of two regulatory mechanisms, patent extension and take-back regulation, on inducing drug manufacturers to go green. Academic/practical relevance: One incentive suggested by the European Environmental Agency is a patent extension for a company that redesigns its already patented pharmaceutical to be more environmentally friendly. This incentive can encourage both the development of degradable drugs and the disclosure of technical information. Yet, it is unclear how effective the extension would be in inducing green pharmacy and in maximizing social welfare. Methodology: We develop a game-theoretic model in which an innovative company collects monopoly profits for a patented pharmaceutical but faces competition from a generic rival after the patent expires. A social-welfare-maximizing regulator is the Stackelberg leader. The regulator leads by offering a patent extension to the innovative company while also imposing take-back regulation on the pharmaceutical industry. Then the two-profit maximizing companies respond by setting drug prices and choosing whether to invest in green pharmacy. Results: The regulator’s optimal patent extension offer can induce green pharmacy but only if the offer exceeds a threshold length that depends on the degree of product differentiation present in the pharmaceutical industry. The regulator’s correspondingly optimal take-back regulation generally prescribes a required collection rate that decreases as its optimal patent extension offer increases, and vice versa. Managerial implications: By isolating green pharmacy as a potential target to address pharmaceutical eco-toxicity at its source, the regulatory policy that we consider, which combines the incentive inherent in earning a patent extension on the one hand with the penalty inherent in complying with take-back regulation on the other hand, serves as a useful starting point for policymakers to optimally balance economic welfare considerations with environmental stewardship considerations.

scholarly journals How Do Prior Ties Affect Learning by Hiring?

2018 ◽  
Vol 46 (2) ◽  
pp. 287-320 ◽  
Author(s):  
Vivek Tandon ◽  
Gokhan Ertug ◽  
Gianluca Carnabuci
Keyword(s):  
Organizational Learning ◽  
Knowledge Base ◽  
Learning Outcomes ◽  
Theoretical Understanding ◽  
Explorative Learning ◽  
Managerial Implications ◽  
Exploitative Learning ◽  
Using Data ◽  
Electronics And Electrical ◽  
New Hires

Research has shown that hiring R&D scientists from competitors fosters organizational learning. We examine whether hiring scientists who have many collaborative ties with the hiring firm prior to the mobility event produces different learning outcomes than hiring scientists who have few or no such ties. We theorize that prior ties reduce explorative learning and increase exploitative learning. Namely, we posit that prior ties lead the hiring firm to focus on that part of a new hire’s knowledge with which they are already familiar and that they help appropriate the new hire’s newly generated knowledge. At the same time, prior ties induce new hires to search locally within the hiring firm’s knowledge base and to produce more incremental, lower-impact innovations. Using data on R&D scientists’ mobility in the Electronics and Electrical Goods industry, we find broad support for our hypotheses. Our results extend our theoretical understanding of learning-by-hiring processes and bear practical managerial implications.

Enhancing participation through organizational drivers

2020 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Fernando Ruiz-Pérez ◽  
Álvaro Lleó ◽  
Elisabeth Viles ◽  
Daniel Jurburg
Keyword(s):  
Job Satisfaction ◽  
Social Influence ◽  
Self Efficacy ◽  
Employee Participation ◽  
Research Literature ◽  
Structural Equations ◽  
Content Type ◽  
Individual Outcomes ◽  
Managerial Implications ◽  
Using Data

PurposeThis paper unifies previous research literature on employee participation in continuous improvement (CI) activities through the development and validation of a conceptual model. The purpose of this model is to illustrate how organizational drivers foster organizational and individual enablers which, in turn, strengthen employee participation in CI. The article also discusses the results and managerial implications.Design/methodology/approachFirstly, the article introduces the main variables affecting employee participation in CI, looking at the different possible relationships proposed in existing literature. In accordance with the Kaye and Anderson (1999) framework, these variables are categorized into organizational drivers, organizational and individual enablers and individual outcomes. Based on these categories, a model was put forward and empirically validated using data collected from three Spanish companies (n = 483) and using partial least squares structural equations modelling (PLS–SEM).FindingsA model was put forward, proposing PIRK systems (power, information, rewards, knowledge) as the main organizational driver of employee participation in CI activities. PIRK impacts positively on social influence (organizational enabler), self-efficacy and job satisfaction (individual enablers). These enablers, together with employee intention of participating, help determine employee participation in CI activities.Practical implicationsOrganizations with CI programmes should develop systems based on employee empowerment, information, rewards and knowledge in order to foster their self-efficacy and seek out a culture where social influence may help to improve job satisfaction. By suitably managing these organizational drivers, managers can help to further develop certain organizational and individual enablers responsible for fostering employee participation in CI activities.Originality/valueBy unifying different behavioural and CI-related frameworks, this paper carries out an in-depth study into the process of fostering employee participation as the key aspect in helping organizations sustain CI programmes. This paper shows the importance of managing PIRK organizational drivers as levers in the process of developing certain organizational and individual enablers, which are responsible for enhancing employee participation in CI.

Truthful Mechanisms for Medical Surplus Product Allocation

2020 ◽  
Vol 22 (4) ◽  
pp. 735-753 ◽  
Author(s):  
Can Zhang ◽  
Atalay Atasu ◽  
Turgay Ayer ◽  
L. Beril Toktay
Keyword(s):  
Private Information ◽  
Value Added ◽  
Information Provision ◽  
Problem Definition ◽  
Preference Ranking ◽  
Additional Increase ◽  
Healthcare Facilities ◽  
Selection Decisions ◽  
Managerial Implications ◽  
Recipient Selection

Problem definition: We analyze a resource allocation problem faced by medical surplus recovery organizations (MSROs) that recover medical surplus products to fulfill the needs of underserved healthcare facilities in developing countries. The objective of this study is to identify implementable strategies to support recipient selection decisions to improve MSROs’ value provision capability. Academic/practical relevance: MSRO supply chains face several challenges that differ from those in traditional for-profit settings, and there is a lack of both academic and practical understanding of how to better match supply with demand in this setting where recipient needs are typically private information. Methodology: We propose a mechanism design approach to determine which recipient to serve at each shipping opportunity based on recipients’ reported preference rankings of different products. Results: We find that when MSRO inventory information is shared with recipients, the only truthful mechanism is random selection among recipients, which defeats the purpose of eliciting information. Subsequently, we show that (1) eliminating inventory information provision enlarges the set of truthful mechanisms, thereby increasing the total value provision; and (2) further withholding information regarding other recipients leads to an additional increase in total value provision. Finally, we show that under a class of implementable mechanisms, eliciting recipient valuations has no value added beyond eliciting preference rankings. Managerial implications: (1) MSROs with large recipient bases and low inventory levels can significantly improve their value provision by appropriately determining the recipients to serve through a simple scoring mechanism; (2) to truthfully elicit recipient needs information to support the recipient selection decisions, MSROs should withhold inventory and recipient-base information; and (3) under a set of easy-to-implement scoring mechanisms, it is sufficient for MSROs to elicit recipients’ preference ranking information. Our findings have already led to a change in the practice of an award-winning MSRO.

scholarly journals An examination of linkages between corporate social responsibility and firm performance: Evidence from Moroccan listed firms

2021 ◽  
pp. 636-646
Author(s):  
Souhaila Kammoun ◽  
Youssra Ben Romdhane ◽  
Sahar Loukil ◽  
Abdelmajid Ibenrissoul
Keyword(s):  
Corporate Social Responsibility ◽  
Firm Performance ◽  
Social Responsibility ◽  
Positive Association ◽  
Social Enterprises ◽  
Listed Firms ◽  
Managerial Implications ◽  
Using Data ◽  
Set Up ◽  
Corporate Social

This article analyzes the complexity of the linkages between corporate social responsibility (CSR) and firm performance in Morocco and to decompose this complexity through a bidirectional sense of causality. Using data surveyed from 74 Moroccan listed firms, we conduct an econometric modeling to measure this relationship bilaterally and to investigate the underlying factors behind this association. The empirical study proves the existence of a positive association between CSR and firm performance in both directions in the Moroccan context and suggests that the more social enterprises are, the more they achieve better financial results. The mutual linkage between social and financial aspects allows us to draw some managerial implications and set up further research directions.

scholarly journals Conflict Management Model of Organization from Molucca’s Cultural Perspective

2020 ◽  
Vol 55 (4) ◽  
Author(s):  
Albertus Fenanlampir
Keyword(s):  
Personality Traits ◽  
Purchase Intention ◽  
Structural Equation ◽  
Positive Impact ◽  
Equation Modeling ◽  
Cultural Perspective ◽  
Mediating Role ◽  
Foreign Products ◽  
Managerial Implications ◽  
Using Data

The purpose of this research is to examine the influence of consumer sentiments on purchase intention toward foreign products and to determine which personality traits are responsible for the formation of consumer sentiments. In this study, we employed Structural Equation Modeling to test the research model using data collected from a survey of 400 young Vietnamese consumers in Ho Chi Minh City. The results provide empirical evidence of the positive impact of consumer cosmopolitanism and xenocentrism on consumers’ purchase intention toward foreign products. Furthermore, through this study, we indicated that certain personality traits shape consumer sentiments. Generally speaking, in the context of foreign consumption, there is an enhanced link between personality traits and purchase intention via the mediating role of consumer sentiments. Theoretical and managerial implications are also discussed.

Sign in / Sign up

Export Citation Format

Share Document