Browsing by Author "Vilkkumaa, Eeva"

Filter results by typing the first few letters
Now showing 1 - 20 of 40
  • Advanced Analytics Success Factors - A Case Study
    (2018) Mattila, Olli-Pekka
     School of Business | Master's thesis
    Companies are increasingly taking into use advanced analytics solutions. Advanced analytics solutions are computer programs that analyze data, make predictions on the future, and give optimization-based recommendations on courses of action for achieving pre-determined business goals. Analytics solutions employ sophisticated statistical and mathematical models, and are often offered by third parties. Companies use analytics solutions to improve the efficiency of their operations. This thesis studies whether the distinction between analytics and advanced analytics made in literature is well-founded. The second aim of this study is to find out, what contributes to an analytics initiative’s success. The study begins with a literature review synthesizing the findings of previous analytics research. The resulting synthesis identifies four distinct stages in an analytics project. They are acquiring data, transforming it into insights, communicating the insights, making business decisions, and finally implementing the decisions. Factors that contribute to each stage’s success are identified. The hypotheses that were developed in the theoretical part of the thesis are subsequently tested empirically using the single case study method and semi-structured interviews. The case study confirms the findings of earlier research. Analytics can be viewed as a process with clearly identifiable stages. Specific measures can be taken to improve the success of each stage. The results obtained suggest that an analytics initiative should always be preceded by a thorough goal definition stage. This is a finding that earlier research has not emphasized sufficiently. The study offers business executives a clear roadmap for managing analytics initiatives. It formulates clear action points and allocates parties the responsibility for executing them. The study also highlights some ordinary pitfalls preventing companies from fully benefitting from the results of analytics initiatives. Finally, the study points out new interesting research opportunities in the intersection of information systems science and cognitive science. A key difficulty in using analytics effectively is that the reasoning behind the insights created by the solutions are often complex. Cognitive science could provide us tools for making the insights easier to digest. Lastly, the study highlights that process decoupling will eventually be applied to analytics initiatives. Future studies should research how the stages of an analytics initiative can be separated from each other, and outsourced to parties performing them the most effectively.
  • Aihioiden priorisointi ja portfolioanalyysi ennakoinnissa
    (2011) Kännö, Juha
     Perustieteiden korkeakoulu | Bachelor's thesis
  • Approaches to Group Decision Support in Robust Portfolio Modeling
    (2008) Vilkkumaa, Eeva
     Helsinki University of Technology | Master's thesis
    Methods of multi-criteria decision analysis (MCDA) provide normative support for decision making processes. Out of these methods, Robust Portfolio Modeling (RPM) helps decision makers (DMs) to select the best possible subset or portfolio of available projects in the presence of scarce resources. The RPM methods provide a computationally efficient way of generating non- dominated portfolios by accommodating incomplete preference information. This Thesis extends the RPM methods to group decision making context, where the different and possibly conflicting interests of multiple DMs need to be synthesized to obtain a satisfactory compromise. As in the single DM case, the information may be given with the preferred accuracy, and it is accommodated by set inclusion without the need for averaging or randomization. The methods also allow the group weight information describing the possible inequality in the DMs' influence to be incomplete. A distinction between individual and joint approaches is made. In the individual approach the group choice is based on the DMs' individually non-dominated sets. The joint approach seeks to aggregate the DMs' individual information into a single preference model. A few decision rules with method-specific variants are presented for generating decision recommendations. Based on an illustrative case study, the methods seem computationally efficient and provide robust decision recommendations. As in the single DM case, the group RPM methods are transparent and do not necessarily require mathematical expertise from the DMs. Owing to computational efficiency, multiple iterations may be carried out, whereby additional preference information can be elicited and utilized as the process evolves. While the main contribution of this Thesis is the development of efficient group methods for portfolio selection problems with incomplete information, also methods for generating group weight information sets based on the DMs' assessments are presented.
  • Bayesian-adjusted estimates in project selection - a comparison study of Bayesian and non-Bayesian decision makers with empirical evidence from the pharmaceutical industry
    (2017) Tran, Tri
     School of Business | Master's thesis
    Companies select projects to invest in based on uncertain estimates of their performance. Theories and empirical evidence suggest that if the uncertain estimates are taken at face value, the true performance of the selected projects tends to be lower than estimated, causing the decision makers (DMs) to experience post-decision disappointment. Taking prior information into account through Bayesian adjustment can result in more realistic estimates of the project performances and thus higher expected performance among the selected projects. However, Bayesian adjustment makes it less likely to predict extreme outcomes and, consequently, may lead to missing out on big wins. This thesis studies the differences in the investment strategies of Bayesian and non-Bayesian DMs and outcomes of these strategies. This is done by employing a combined approach of both qualitative and qualitative research methodology. The quantitative approach of this thesis is in the form of a mathematical model that is used both to derive analytic results and for Monte Carlo simulation. The qualitative approach of this thesis is utilized to test theoretical findings empirically. The key results reveal that when fewer than 50% of project proposals would truly perform well (e.g., have truly positive NPV), a Bayesian DM invests in too few and a non-Bayesian DM to too many projects. Moreover, the average ex post performance of the projects funded by a Bayesian DM is higher than that of a non-Bayesian DM. However, a non-Bayesian DM will have a higher proportion of funded projects that result in big wins, but also a higher proportion of projects that result in losses. If, on the other hand, more than 50% of project proposals would truly perform well, the roles of a Bayesian and non-Bayesian DM are reversed. The less accurate the performance estimates, the more pronounced the differences between the investment outcomes of a Bayesian and a non-Bayesian DM. These analytic results are testified empirically in the R&D portfolio selection decisions in the pharmaceutical industry. Accordingly, the decision-making environment of the pharmaceutical industry displays characteristics of an environment with high estimate errors that amplify the differences in outcomes of a Bayesian DM’s versus a non-Bayesian DM’s investment decisions. As the DMs in this industry show quintessential characteristics of non-Bayesian DMs and the observed empirical outcomes perfectly coincide with the theoretical outcomes for non-Bayesian investment decisions, our theoretical findings are well-reflected empirically. From a theoretical perspective, this thesis contributes novel analytic results on the differences between the investment strategies adopted by Bayesian and non-Bayesian DMs and validates these results with empirical evidence. From a practitioner’s point of view, this thesis gives insights into how estimation uncertainties affect investment decisions and outcomes. Understanding such effects can help managers make better-informed decisions.
  • Comparing external data monetization of two analytics products – case study in the telecommunications industry
    (2021) Savolainen, Iiris
     School of Business | Master's thesis
    Monetizing growing amounts of company data is an intriguing idea for many practitioners. Data monetization becomes particularly relevant in industries where the traditional business is declining, pushing companies to seek new revenue sources to stay competitive. However, most companies still struggle with their data monetization efforts, implying a need to investigate the issues hindering data monetization potential and enablers driving success. The novelty of the research field and its industry-specific nature suggest conducting explorative studies. This thesis examines the topic in the data-intensive telecommunication industry, focusing on identifying challenges and enablers related to external data monetization with analytics products in a case company. Two analytics products are compared based on expert interviews using a seven-step process framework for external data monetization. The process phases include 1) opportunity mapping and data strategy preparation, 2) potential planning and use case definition, 3) legal and compliance alignment, 4) data collection and preparation, 5) technological arrangements, 6) data pricing strategy and 7) market entrance planning. The results show that the main challenges with analytics productization in a case company include data pricing for maximal profit accuracy, combining data sources and ensuring reliable results, as well as modeling, justifying and communicating customer value. Also, securing sufficient management’s support and investments and balancing with constant organizational changes complicate analytics productization. The analysis implies that enhancing market understanding by focusing on certain customer segments helps create more relevant use cases, ensure sufficient demand, and model customer perceived value. Moreover, measuring customer case and piloting success improves the customer value proposition's concreteness, further supporting pricing, marketing, and sales argumentation. Then again, treating data as an asset and investing in consistent data architecture and data management supports external data monetization with multiple data sources for reliable results and value. Finally, emphasizing education about external data monetization and analytics products will likely boost future initiatives' success. The explorative case study results contribute to theory by using analytics product as an external data monetization offering and testing a practical process framework for academic purposes, similarly providing direction for further research and validation in other organizations and markets.
  • Determinants of central government employee turnover in Finland: A competing risk analysis
    (2021) Tarvainen, Ella
     School of Business | Master's thesis
    In developing and implementing human resource management, the employer needs detailed information on personnel turnover and its reasons. The retirement of baby boomers, digital technology transformation, and competition for talented workforce increase labor demand, which underlines the need for this information. Furthermore, the Finnish central government is currently focusing on improving its competitiveness as an employer and preparing for the significant recruitment need to be brought by the aging workforce and the need for skilled employees for the transformation in digital technology. This thesis aims to examine the external mobility patterns in the Finnish central government using ten years of personnel data and a competing risk analysis. Employee data of demographics and job-related characteristics can yield important signals to predict the likelihood of departure. The aim is to identify potential determinants that affect the employment duration to provide insight into employee turnover patterns and perspectives that the government can consider when developing its employer image. The cause-specific hazard model and the Fine-Gray subdistribution hazard model can be used to analyze simultaneously multiple variables that affect the employment duration taking into account the presence of other possible events, such as retirement. The findings are in line with the previous turnover research suggesting that turnover may not be an issue in terms of quantity, but quality, as experts and young adults are more likely to change jobs. According to the results, government personnel may not be motivated by financial rewards, but perhaps public service ideals and other benefits. In addition, the gender-turnover relationship is strongly dependent on whether the personnel turnover is studied with or without the security sector.
  • Developing value-based outcome measures for oral healthcare
    (2019) Sormunen, Markus
     School of Business | Master's thesis
    Recent focus in healthcare has been on developing value-based treatment models where the central goal is to produce meaningful health outcomes for patients. The inability of the current restorative treatment model to facilitate oral health improvement has been widely recognized and there is increasing demand to make part of the compensation of dental practitioners’ dependent on achieving oral health outcomes. However, value-based compensation models are currently absent and limited literature exists on value-based oral healthcare. The development of quality measures for oral healthcare has fallen behind of other areas of healthcare and is one of the main barriers hindering oral health improvement. Most of the currently existing oral health quality indicators focus on processes of care rather than health outcomes. However, without corresponding outcome measures these quality indicators provides only limited information. Limited literature exists on the development of health outcome measures for oral healthcare. The aim of this thesis was to develop value-based oral health outcome measures for dental caries and periodontal diseases based on the currently available information from electronic health records. Due to the limited literature on oral health outcome measurement, academic literature was examined to determine what constitutes successful treatment outcomes for dental caries and periodontal diseases from an oral health perspective. This was defined as the preservation of natural tooth structure and sustainable self-management of oral diseases, which was then translated into oral health outcome measures. Seven oral health outcome measures were developed based on the available information and tested for face validity, feasibility of data collection and discriminative validity. The largest barrier hindering oral health outcome measurement was found to be the insufficient recording practices of dental practitioners. Only three of the seven identified outcome measures could be reliably measured due to feasible data collection. Two of the developed measures: cavitation free clinical examinations and average number of new cavitated surfaces were considered valid and relevant outcome measures for dental caries. The limited availability of key periodontal information was especially problematic. The main finding of this thesis is that currently preventive and early treatment of dental caries and periodontal diseases are underutilized and key clinical indicators for monitoring the effectiveness of these interventions are not routinely recorded. Therefore, the current treatment model is focused on treating the symptoms of manifested disease rather preserving oral health. The results suggest that significant health improvement could be achieved by reorienting service provision toward a more preventive focus.
  • Effects of many conflicting objectives on decision-makers’ cognitive burden and decision consistency
    (2025-04-01) Kivikangas, J. Matias; Vilkkumaa, Eeva; Blank, Julian; Harjunen, Ville; Malo, Pekka; Deb, Kalyanmoy; Ravaja, Niklas J.; Wallenius, Jyrki
     A1 Alkuperäisartikkeli tieteellisessä aikakauslehdessä
    Practical planning and decision-making problems are often better and more accurately formulated with multiple conflicting objectives rather than a single objective. This study investigates a situation relevant for Multiple Criteria Decision Making (MCDM) as well as Evolutionary Multi-objective Optimization (EMO), where the decision-maker needs to make a series of choices between nondominated options characterized by multiple objectives. The cognitive capacity of humans is limited, which leads to cognitive burden that influences human decision-makers’ decisions. We measure how the varying number of objectives influences cognitive burden in a laboratory study, and the impacts that this burden has on the decision-makers’ behavior and the consistency of their decisions. We use psychophysiological, behavioral, and self-report methods. Our results suggest that a higher number of objectives (i) increases cognitive burden significantly, (ii) leads to adopting strategies in which only a limited number of objectives is considered, and (iii) decreases decision consistency.
  • Evaluating optimal portfolio decisions through return, risk, and impact dimensions
    (2022) Aalto, Maria
     School of Business | Master's thesis
  • Explaining reviewer trustworthiness from reviewer characteristics: a regression model
    (2020) Dang, Hao
     School of Business | Master's thesis
    Online consumer reviews have an essential role in online consumer’s buying decisions and e-commerce sales as consumers trust them more than the information provided by the seller. The reviews supposedly give indications to previous consumer’s buying experiences and satisfaction, giving potential buyers more perspective on the considered product or service. However, the anonymity, the easiness of leaving a review, the increasing amount of reviews and review websites available, and the benefits of good reviews to a seller have opened the online reviews for manipulation and fraud. This fragile trust and uncertainty have hurt the potential buyers, the sellers’ credibility and sales, the review platform’s credibility, and the reviewer’s credibility. One of the ways to address this issue is finding trustworthy reviewers as they write reliable reviews, helping potential consumers reach a credible information source. A previous study in 2017 has proposed a novel model of explaining reviewer trustworthiness from reviewer characteristics. As an attempt to explore the latest research and the novel model explaining reviewer trustworthiness, this thesis aims to verify these reviewer characteristics’ contribution in solving the reliability of a reviewer on a similar dataset. Also, further analysis is conducted on the model and its components to obtain a well-performing and robust model to explain reviewer trustworthiness using reviewer characteristics, including involvement, positivity, experience, competence, reputation, and sociability. All reviewer attributes in the analysis are confirmed to be positively related to reviewer trustworthiness, which is computed by using a more robust and generalizable method than in the previous study. Productivity and recent activeness of a reviewer have been better representatives for the experience than the number of years on an online platform. Sociability, out of the attributes in scope, has been identified as having the least effect on reviewer trustworthiness, implicating that sociability should not be the top or only factor to judge the reliability of a reviewer. A modified inverse Gaussian model has been identified and tested in this paper to perform well and robust in explaining reviewer trustworthiness from reviewer characteristics in a straightforward and computationally efficient manner.
  • Facilitating public procurement processes with multi-criteria decision analysis
    (2023) Koskela, Maria
     School of Business | Master's thesis
    Public procurement is a multi-staged and complex process where the selection of the best tender is considered a paramount objective. Decision making plays a vital role in public procurement processes. However, the European Union legislation restricts the autonomy of decision making by defining the framework for public procurement activities in EU member states. In public procurement, a contract can be awarded based on the lowest price or the most economically advantageous tender. Especially when evaluating the most economically advantageous tender, the identification of the best tender can be considered a multi-criteria decision making problem, the solution to which can be facilitated by multi-criteria decision analysis, MCDA. Previous research on the application of MCDA in public procurement has essentially focused on how it can facilitate the evaluation of tenders. However, it is recognized that MCDA can aid in problem-solving more broadly beyond the evaluation of alternatives. Despite this recognition, there is limited previous research on the subject and very little empirically backed evidence of MCDA’s broader benefits in public procurement processes. This thesis aims to fill the gap in previous research by exploring how MCDA can be utilized in public procurement by integrating it as a comprehensive part of the procurement process, from identifying the need for procurement to formulating the contract and monitoring its implementation and execution. The research method used is a qualitative case study, preceded by an academic literature review, summarizing the most relevant previous findings. The case study explores the HX fighter program, being the most expensive defence procurement in the history of Finland. The HX fighter program applied a unique MCDA model that had a central role in its public procurement process. The results of the case study confirm observations from previous literature, which had not been conclusively demonstrated. The findings suggest that by utilizing MCDA in the procurement process, various aspects of the process and even its outcomes can be influenced in multiple ways. The author hopes that the results of this thesis will encourage practitioners in public procurement to integrate MCDA more comprehensively into their public procurement processes.
  • Forecasting shared-bike system demand
    (2021) Kivinen, Juuso
     School of Business | Master's thesis
  • A framework for evaluating the risk management practices of metal prices in firm X
    (2020) László, Ben
     School of Business | Master's thesis
    Risks related to commodity prices can be managed through financial hedging. While risk management procedures have been studied widely in both finance and management literature, only a few studies have been conducted that adjoin both of these disciplines. From a practitioner perspective, recent literature on this topic has been too general to result in implementable decision recommendations. The overcome this issue, there is a need for in-depth, company-specific case studies. The objective of this thesis is to study the most prominent commodity prices in a case company operating in the metal recycling industry, and to assess whether this company can enhance their current risk management practices by adopting systematic financial hedging as a part of their everyday business. This objective is pursued through both qualitative and quantitative methods. In the qualitative part, employees and top management have been interviewed in order to map the most relevant risks within the recycling industry, to form a holistic picture of the company’s prevalent risk management practices and to identify factors for the quantitative analysis. The quantitative analysis focuses on comparing the company’s current commodity risk management practices with the possible performance of implementing systematic financial hedging practices to their prevalent mode of operation. Market price forecasts for copper and nickel were modelled through a Monte Carlo simulation utilizing the Ornstein-Uhlenbeck process. The key findings of this thesis are two-fold. The specific industry is subject to multiple frictions and elements which greatly complicate price risk management. In addition, as currently the company’s operations and pricing policies are not standardized, systematic hedging through financial means may introduce more problems than it would solve. However, with the proposed development initiatives as well as together with discretionary and careful consideration, systematic hedging can be achievable.
  • Identifying and visualizing a diverse set of plausible scenarios for strategic planning
    (2022-04-16) Seeve, Teemu; Vilkkumaa, Eeva
     A1 Alkuperäisartikkeli tieteellisessä aikakauslehdessä
    When making long-term strategic decisions, organizations may benefit from characterizing their future operational environment with a set of scenarios. These scenarios can be built based on combinations of levels of uncertainty factors describing, e.g., alternative political or technological developments. However, the number of such combinations grows exponentially in the number of the uncertainty factors, whereby the selection of a few combinations to work as a basis for scenario development can be difficult. In this paper, we develop a method for identifying a small but diverse set of plausible combinations of uncertainty factor levels. The method filters an exponentially large set of possible combinations to a smaller set of most plausible combinations, as assessed by the consistencies of the pairs of uncertainty factor levels in the combinations. To support the selection of the final set of combinations from the most consistent ones, we formulate a weighted set cover problem, the solution to which gives the smallest number of maximally consistent combinations that together cover all uncertainty factor levels. Moreover, we develop an interactive software tool utilizing Multiple Correspondence Analysis to visualize the consistency and diversity of the combinations, thus improving the transparency and communicability of the methods. This paper also presents a real case in which our method was used to identify a set of plausible scenarios for the Finnish National Emergency Supply Organization to support their strategic decision making.
  • Kustannustehokkaat riskienhallintatoimenpiteet kuljetusverkostossa
    (2015-05-15) Lanne, Joonas
     Perustieteiden korkeakoulu | Bachelor's thesis
  • Lisäinformaation arvo monikriteerisessä projektiportfoliovalinnassa
    (2015-07-29) Hirvonen, Jussi
     Perustieteiden korkeakoulu | Bachelor's thesis
  • Menetelmä Markowitzin mallin parametrien estimointiin
    (2016-01-27) Nyman, Lauri
     Perustieteiden korkeakoulu | Bachelor's thesis
  • Model-based decision processes for agenda building and project funding
    (2014) Vilkkumaa, Eeva
     School of Science | Doctoral dissertation (article-based)
    Essentially all organizations need to recognize relevant future developments in their operational environment as a backdrop for building strategic priorities which are typically implemented by choosing corresponding actions (such as R&D projects). These interlinked processes – most notably horizon scanning, strategic priority-setting and project selection – can all be framed as decision problems in which a subset or portfolio of alternatives is to be selected subject to limited resources and other relevant constraints. They can therefore be approached with methods of portfolio decision analysis (PDA) in order to maximize the value that the selected portfolio can be expected to yield and also to improve the transparency and quality of decision processes. This Dissertation develops PDA methods to support the above decision processes, particularly in contexts where there are significant uncertainties. These methods capture uncertainties through set inclusion of feasible parameters and probability distributions. The methods accommodate the possibly conflicting preferences of multiple decision-makers, and they help identify portfolios that are resilient across a range of scenarios about the future. They also help mitigate so-called post-decision disappointment, which results from the fact that those projects whose values have been overestimated are more likely to be selected. The methods in this Dissertation can also be used to develop optimal project funding policies which maximize the average value of the selected project portfolio or the number of those projects whose values are exceptionally high. They also guide the reduction of uncertainties by indicating about which projects it is optimal to acquire additional value estimates such that the resulting increase in the value of the portfolio exceeds the costs of acquiring such estimates.
  • Modeling uncertainties in portfolio decision analysis
    (2012) Vilkkumaa, Eeva
     School of Science | Licentiate thesis
  • Monte Carlo -menetelmä optioiden hinnoittelussa
    (2015-09-10) Laakkonen, Niko
     Perustieteiden korkeakoulu | Bachelor's thesis