Sedan den finanskris som uppstod år 2008 har ökade krav ställts beträffande säkerhet ochstabilitet inom den finansiella sektorn. Av den orsaken har etablerade aktörer, vilka omfattas avde alltmer extensiva regelverken, påförts ytterligare krav avseende exempelvis tillsyn ochlikviditet. De ökade säkerhetskraven har, i sin tur, tvingat berörda aktörer att agera merrestriktivt beträffande finansiell innovation och vid utvecklandet av nya finansiella lösningar. Den tekniska utvecklingen har möjliggjort för uppkomsten av nya typer av betaltjänster ochprodukter. Det har resulterat i att etablerade finansiella aktörer, under det senaste decenniet, harmött nya utmaningar i form av en ökad konkurrens från fintechbolag vilka, vid sidan avbefintliga regelverk, har utvecklat innovativa tjänster och produkter specialiserade inom ettspecifikt led inom kundkontaktskedjan. Med anledning av ikraftträdandet av det andrabetaltjänstdirektivet omfattas även fintechbolag av de bestämmelser som reglerarbetaltjänstmarknaden. Genom införandet av regelverket utökas omfattningen till att äveninbegripa leverantörer av kontoinformationstjänster och betalningsinitieringstjänster, så kalladetredjepartsleverantörer. Syftet med det andra betaltjänstdirektivet är bland annat att främjakonkurrens samt att effektivisera den finansiella marknaden. Samtidigt får inte den finansiellastabiliteten äventyras på bekostnad av ifrågavarande ändamål. För att främja finansiell innovation har vissa nationella tillsynsmyndigheter vidtagit olikaregleringsrelaterade åtgärder, såsom exempelvis en regulatorisk sandlåda, en innovationshubbeller ett innovationscenter. Med åtgärderna avses att med olika medel tillvarata den potentialsom fintech har att erbjuda finansmarknaden. Regleringsrelaterade åtgärder, vidtagna pånationell nivå, måste emellertid utvecklas och förhållas till gällande regelverk och får inte sättakonsumentskyddet på spel. I förevarande uppsats behandlas huruvida såväl det andra betaltjänstdirektivet som nationelltvidtagna regleringsrelaterade åtgärder förmår att främja tredjepartsleverantörersinnovationsförmåga på betaltjänstmarknaden, särskilt med beaktande av deras möjligheter attkonkurrera på den finansiella marknaden, utan att det sker på bekostnad av det finansiellasystemets stabilitet och säkerhet.

金融科技因為能大幅降低金融活動中的交易成本與門檻，同時打破傳統金融交易資訊不及時的情況，因此能創造以往未有的商業價值。其中P2P Lending即透過電子化技術創造交易平台媒合資金提供者與需求者的微型授信服務，因為省去傳統金融機構中介的成本，故能提升供需雙方效益。然而特殊的營運方式使資金提供者須承擔更高風險，實際上P2P Lending亦曾發生重大詐騙與倒帳事件，因此使英美中政府加強監管，相較之下，我國仍維持不納入金融監管原則，因此本研究試圖以Lending Club具有代表性的案例，提供投資者選擇投資標的的建議。 本研究搜集Lending Club自2007年至2011年42538筆已發行之借貸，在111個變數中使用 Pearson Correlation以及Information gain，並輔以文獻回顧進行變數選擇挑選22個變數。在搭配Dropout技術與透過網格搜索分析最佳化演算法、批次訓練樣本數、訓練次數等參數配置後，本研究訓練得到在測試集準確度達76%的類神經網路模型。經模擬後發現，類神經網路ROI的平均值為9.40，高於對照組7.02，經檢定驗證此差異結果可以採信，因此類神經網路能有效的給予投資人有效的投資建議。

本文以全球第一個演算法交易雲端平台－Quantopian進行研究，藉由平台社群討論區內公開之演算法交易策略，透過交易策略篩選和初步優化，以演算法交易策略為投資標的，搭配不同權重策略建構投資組合。權重策略部分，本文提出適用於組合式交易策略的績效指標加權 (Performance Index Weighted) 法，應用因子投資的觀念，融合排序相關性較低、不同面向之績效指標作為報酬率驅動因子，並參考Asness et al. (2013) 以因子排序作為權重計算依據，提供了簡單直覺、非最適化求解而且穩健的加權方式，更直接地將交易策略各面向績效的優劣反應在權重上。 根據數值分析，發現組合式交易策略長期而言，整體績效表現平均優於個別演算法交易策略，最小變異、績效指標加權和均等權重投資組合的風險亦明顯低於個別交易策略，且最小變異、績效指標加權和均等權重投資組合在降低投資組合風險的同時，並未犧牲過多報酬，風險調整後績效表現優於個別交易策略。而績效指標加權投資組合之年化報酬率、風險衡量和風險調整後績效表現皆優於最小變異、平均數－變異數、均等權重的加權投資組合，此種權重策略可使投資組合之夏普比率 (Sharpe ratio) 顯著提升，且投資組合的風險大幅降低，最大跌幅 (Max drawdown) 在四年半的實驗區間內降至10%以下的水準，風險調整後績效優異。 透過Quantopian社群演算法交易平台，個人投資者也能站在巨人的肩膀上學習，集合眾人的力量，憑藉量化交易創造出和機構法人一樣具有競爭力的投資組合。如Chan (2009) 所言，個人投資者也能憑藉量化交易，設計一套演算法交易策略。 / Quantopian is a crowd-sourced hedge fund which allows members on the platform to develop their own algorithmic strategies and even get capital allocations from Quantopian. In this paper, we constructed portfolios by Quantopian trading platform and proposed Performance Index Weighted method which generate consistently profit in our study. First, we filtered algorithmic trading strategies shared on the Quantopian community and improved the performance slightly. Second, we combined multiple algorithmic strategies with varied portfolio weight method, such as minimize-variance, performance index weighted, mean-variance, and equal weighed method to construct a portfolio. To elaborate, Performance Index Weighted portfolio is actually an application of factor investing, in which the portfolio weight depends on the ranking of performance index (factors), and these index measure returns, risk, and also risk-adjusted returns, which truly reflects how well the algorithmic strategy is. As a result, we used the performance index as a return driver and invested more in well-ranked strategies directly. Performance index weighted is a simple, robust, and fully intuitively way to construct a portfolio. In numerical analysis, we found that using multiple strategies to construct a portfolio could generate better performance than a single algorithm strategy on average. Moreover, the annual returns, risk measure, and risk-adjusted returns of Performance Index Weighted portfolio turn out to be better than minimize-variance portfolio, mean-variance portfolio, and equal weighted portfolio. As a result, Performance Index Weighted portfolio has significantly higher Sharpe ratio and lower Max Drawdown (lower than 10% in our out-of-sample test) than other portfolios, which shows excellent risk-adjusted performance. Most important of all, retail traders could learn more precisely by standing on the shoulders of giants through Quantopian trading platform. Also, by collecting wisdom from the crowd, we create an opportunity for retail traders to construct competitive portfolios just as institutional investors do.

金融科技是當前歐美先進國家之潮流趨勢，由於資訊科技的進步，現今金融業者面對外在競爭者不再只侷限於傳統金融業者，新創科技業者也加入角逐金融服務這塊大餅，破壞式創新正在我國加速發酵中。金融科技新興商業模式的興起，涉及各個不同面向與關鍵成功因素，這些面向與關鍵因素之間的相對權重，乃是相關產業與政府部門值得深入探討的課題。 本研究旨在探討台灣金融科技關鍵因素之權重分析，藉由相關文獻的蒐集與彙整，建立層級架構，主層級架構包含四個面向：政府面向指標、業者面向指標、顧客面向指標、以及技術安全指標，藉由此四項指標整合出各項次層級之影響因素，透過層級分析法進行研究分析，整理出各項影響因素的權重排序。 本研究透過市場調查，將問卷對象分為兩類，包括專家以及學生群組，經過問卷調查後發現，不論專家或是學生群組，皆認為「技術安全指標」是金融科技發展中最重要的關鍵指標。在整體問卷實證結果中，關鍵因素之權重排序依次為：「提升消費者信賴程度」(0.0864)、「法規的鬆綁與調整」(0.0563)、「使用者身份加密機制」(0.0523)、「勒索軟體之威脅」(0.0488)、以及「殭屍病毒之威脅」(0.0475)。 不同群組的問卷對象之調查結果顯示，專家群組認為「提升消費者信賴程度」(0.1112) 以及「擴增消費者體驗」(0.0586)為前二重要的影響因子；學生群組認為「提升消費者信賴程度」(0.0630)、以及「使用者身份加密機制」(0.0575)為前二重要的影響因子。專家以及學生群組皆認為「提升消費者信賴程度」為金融科技發展中相對重要的影響因子。 / Financial technology is the current trend of the advanced countries such as Europe and the United States. Due to the progress of information technology, the current financial industry that faces the external competitors are no longer confined to the traditional financial industry, the new technology industry also joined the financial services. Disruptive Innovation is accelerating fermentation. The rise of the emerging business model of financial technology involves various different aspects and key success factors. The relative weight between these and the key factors is the subject of the relevant industries and government departments that are worthy of further study. The purpose of this study is to explore the weight analysis of the key factors of Taiwan's financial science and technology, and to establish a hierarchical structure through the collection and compilation of related literature. The main level structure includes four aspects: government-oriented indicators, industry-oriented indicators, customer orientation, and technical safety Index. Through the four indicators of the integration of the sub-level of the influencing factors, and also through the hierarchical analysis of research and analysis, it is sorted out the impact of the weight of the factors. Through the market survey, the questionnaire will be divided into two categories, including experts and student groups. It is found that regardless of the expert or student groups, both of them think that "technical safety indicators" is the most important financial technology development Key indicators. In the whole questionnaire, the key factors are ranked as follows: "Enhancing the degree of consumer trust" (0.0864), "Relaxation and adjustment of regulations" (0.0563), "User identity encryption mechanism" (0.0523)," the threat of the software " (0.0488), and "the zombie virus threat " (0.0475). The results of the questionnaires of the different groups show that the group of experts considered " Enhancing the degree of consumer trust" (0.1112) and the "Expanded Consumer Experience" (0.0586) as the first two influencing factors; the student groups consider " Consumer trust" (0.0630), and the" user identity encryption mechanism" (0.0575) for the first two important factors. Experts and students consider that "Enhancing the degree of consumer trust" for the development of financial technology is a relatively important factor.

現今科技日新月異，不斷突破創新，產業環境變動的步調也越來越快，新竄出之金融科技(Finance Technology)的應用，使得許多企業越加注重技術方面的研發創新，尤其，善加運用專利資訊能有效節省研發經費與時間。因此如何有效運用專利是企業維持競爭優勢不可或缺的一環。 有鑑於此，本研究搜集近年各國專利資料庫之專利資料，將資料分為三個時期，並區分申請中與已申請之專利資料，透過文字探勘技術與機會探索分析出金融科技之發展與趨勢，了解各時期詞彙間之關聯性與差異，再搭配視覺化工具KeyGraph，以描繪出金融科技領域之相關詞彙關聯趨勢圖，挖掘未來潛在趨勢。 本研究之結果了解金融科技在各時期的趨勢發展變化與尋求脈絡，以及過去各時期之專利佈局，因而從結果中發現金融科技之發展方向主體為支付領域，許多支付科技接連出現在三個時期中。然而近幾年，其他金融領域如投資、融資、保險、資料分析等也漸漸浮出，從本研究之第三個時期的高頻字詞高達34個可看出，可見金融科技之專利發展佈局已快速從支付領域拓展至其他金融領域。本研究所挖掘出之潛在趨勢顯示了未來金融科技領域中將會有五大重點發展領域，分別為服務整合領域之雲端科技、支付領域之生物辨識與穿戴支付與加密貨幣、資料分析領域之機器學習與人工智慧、信息收集與處理領域之遠程信息處理科技、以及理財投資領域之理財機器人。 期望本研究結果能幫助企業，在面臨新科技不斷衝擊產業，而產業不斷尋求創新發展之下，能夠快速檢閱目前市場趨勢，藉此釐清並改善自身之發展策略，以因應外部環境之變動，提供企業作為金融科技發展之策略參考，也能有助於企業釐清與制定金融科技之投資方向，以擁有持續的競爭優勢。 / Nowadays, with the rapid advancement of information technologies, the changes of business environment and the way to deal with the changes are becoming faster and faster. The development and adoption of new financial technologies has made many enterprises pay more attention to the research and development (R&D) initiatives. Besides, making good use of patent information can effectively save the budget and time of R&D, so how to effectively use patent information is an indispensable part for enterprises to maintain their competitive advantages. This study collected the patent data from the national patent database, and divided the data into three periods, and distinguished the data between the applying and the applied patents. Through the text mining techniques and chance discovery, this study explored the development and trends of financial technology and also aimed to understand the relevance and differences between the major terms in each period. Then, with the visual tool, KeyGraph, this study illustrated the associations between related terms, and proposed the potential future trends based on the graphs. The results of this study help monitor the changes of the trends and financial technology’s development in the three periods, and understand the patent portfolios in each period. This study has found that the main direction of financial technology’s development is the payment field. Many technologies related to payment have successively appeared in the three periods. However, in recent years, other financial areas such as investment, financing, insurance, data analysis and other areas are gradually emerging, since we found 34 high-frequency terms in the third period. This also shows that the development of financial technology’s patent portfolios has expanded from payment to other financial areas. The potential trends of financial technology’s development in this study are five areas, namely, technologies of cloud, biometric and wearable payment and cryptocurrency, machine learning and artificial intelligence, telematics technology, and robo-advisors. It is expected that this study can serve as a reference for the development of financial technology, and help enterprises be able to quickly review their current market trends, clarify and improve their own R&D strategies to respond to the changes in the external environment. Also, it is hoped that the results can help enterprises clarify and develop their own investment directions to maintain competitive advantages.

FinTech不僅為金融產業熱門之議題，亦為未來金融產業發展之重大方向，因而多數金融機構投入大量資金作為FinTech相關業務之研發，但企業內部卻對策略發展方向毫無頭緒，導致資源應用不當之情況發生，因此本研究結合學術之工具，改善企業盲目投資之問題，使企業能依據顧客之需求提供全方位之解決方案。 　　本研究採用個案研究法，以我國金融控股公司領導品牌之一為研究對象，藉由與個案公司內部人員會談及其他公開管道蒐集相關資訊並加以分析，探討FinTech對顧客價值主張與金融產業現有業務所帶來之影響，並透過分析企業之自身內部優勢及外部機會形成以FinTech為主軸之創新策略，再進一步深入探討該創新策略之執行及其所衍生出之策略性智慧資本應如何進行管理。 / FinTech is not only a hot issue but also a major direction for the future development of the financial industry. Most financial institutions have invested heavily in FinTech-related research and development, but they have no idea how to develop the strategy. This situation misguided valuable resource to wrong business. So, this research paper applies academic tools to provide a total solution for enterprises on investment based on customer needs. 　　This research paper adopts case study method. The case company is a financial holding company in Taiwan, which is one of leading financial institution. In this year, discussing with company employees and analyzing related data to gauge the impact of customer value proposition of the existing financial industry. Creating an innovative strategy based on FinTech by evaluating the company’s internal strengths and external opportunities. Further, discussing on the implementation of the innovative strategy and how to manage intellectual capital derived from the innovative strategy.

Im ersten Abschnitt der Arbeit werden, neben dem grundlegenden Ablauf, die unterschiedlichen Factoring-Formen und Funktionen erläutert. Es erfolgt eine Abgrenzung zu anderen kurzfristigen Finanzierungsformen. Für diese Arbeit wurden Geschäftszahlen der Jahre 2008 bis 2018 von 106 Factoring-Unternehmen über die elektronische Ausgabe des Bundesanzeigers erhoben. In dem darauffolgenden Abschnitt erfolgt die Arbeit mit den empirischen Daten. Die Daten werden diskutiert, aufbereitet und anschließend ausgewertet. Es werden Entwicklungen am Arbeitsmarkt und der Gesamtwirtschaft beobachtet und im letzten Abschnitt der Arbeit die aktuellen Entwicklungen der Fintechs betrachtet. Dabei wird der Begriff „Fintech“ zunächst definiert und die Unterschiede zu klassischen Geschäftsmodellen kritisch analysiert. Abschließend erfolgt eine Zusammenfassung der Ergebnisse.:1 Einleitung 2 Definition und Abgrenzung des Factorings 2.1 Definition und Formen des Factorings 2.2 Bedeutung und Funktionen des Factorings 2.3 Alternative kurzfristige Finanzierungen und deren Kosten 3. Entwicklung des Factoring-Marktes in Deutschland 3.1 Erhebung und Herkunft der Daten 3.1.1 Statistische Beurteilung – Qualität der Daten 3.1.2 Regression – Schätzen fehlender Werte 3.1.3 Interpretation der Daten 3.2 Einteilung der Unternehmen 3.2.1 Nach Unternehmensgröße laut HGB 3.2.2 Nach Rechtsform 3.2.3 Nach Standort 3.2.4 Nach Gründungsdatum 3.2.5 Nach Wirtschaftsbranche der Factoring-Kunden 3.3 Positionen der Gewinn- und Verlustrechnung 3.3.1 Zinserträge / Provisionserträge 3.3.2 Zinsaufwendungen / Provisionsaufwendungen 3.3.3 Allgemeine Verwaltungsaufwendungen 3.3.4 Wertberichtigungen auf Forderungen 3.3.5 Sonstige Gewinn- und Verlustrechnungspositionen 3.3.6 Ergebnis aus normaler Geschäftstätigkeit 3.4 Positionen der Bilanz 3.4.1 Forderungen und Verbindlichkeiten 3.4.2 Sonstige aktive Bilanzposten 3.4.3 Eigenkapital 3.4.4 Sonstige passive Bilanzpositionen 3.5 Arbeitsmarkt / Anzahl der Mitarbeiter 3.6 Entwicklung der Factoring-Quoten, Kundenzahlen 3.7 Historische Entwicklung und regulatorische Einflüsse 4 Entwicklungen in der Fintech-Branche 4.1 Definition von Fintechs 4.2 Dienstleistungsunterschiede zu klassischen Factoring-Anbietern 4.3 Börse für Factoring 4.4 Kritische Auseinandersetzung 5 Zukünftige Entwicklung 6 Fazit / This bachelor thesis evaluates the development of the german factoring market between the years 2008 and 2018. For the evaluation key figures of annual financial statements, employment market and the factoring branch in general are compared between 164 factoring companies.The thesis also discusses the latest innovation of fintechs and draws a comparison to traditional factoring companies. In conclusion, the results clearly show a growth of the industry within the evaluation period.:1 Einleitung 2 Definition und Abgrenzung des Factorings 2.1 Definition und Formen des Factorings 2.2 Bedeutung und Funktionen des Factorings 2.3 Alternative kurzfristige Finanzierungen und deren Kosten 3. Entwicklung des Factoring-Marktes in Deutschland 3.1 Erhebung und Herkunft der Daten 3.1.1 Statistische Beurteilung – Qualität der Daten 3.1.2 Regression – Schätzen fehlender Werte 3.1.3 Interpretation der Daten 3.2 Einteilung der Unternehmen 3.2.1 Nach Unternehmensgröße laut HGB 3.2.2 Nach Rechtsform 3.2.3 Nach Standort 3.2.4 Nach Gründungsdatum 3.2.5 Nach Wirtschaftsbranche der Factoring-Kunden 3.3 Positionen der Gewinn- und Verlustrechnung 3.3.1 Zinserträge / Provisionserträge 3.3.2 Zinsaufwendungen / Provisionsaufwendungen 3.3.3 Allgemeine Verwaltungsaufwendungen 3.3.4 Wertberichtigungen auf Forderungen 3.3.5 Sonstige Gewinn- und Verlustrechnungspositionen 3.3.6 Ergebnis aus normaler Geschäftstätigkeit 3.4 Positionen der Bilanz 3.4.1 Forderungen und Verbindlichkeiten 3.4.2 Sonstige aktive Bilanzposten 3.4.3 Eigenkapital 3.4.4 Sonstige passive Bilanzpositionen 3.5 Arbeitsmarkt / Anzahl der Mitarbeiter 3.6 Entwicklung der Factoring-Quoten, Kundenzahlen 3.7 Historische Entwicklung und regulatorische Einflüsse 4 Entwicklungen in der Fintech-Branche 4.1 Definition von Fintechs 4.2 Dienstleistungsunterschiede zu klassischen Factoring-Anbietern 4.3 Börse für Factoring 4.4 Kritische Auseinandersetzung 5 Zukünftige Entwicklung 6 Fazit

No description available.

La presente investigación tiene como propósito hacer una revisión de la literatura sobre el uso de las tecnologías disruptivas en el sector financiero y cómo estas se proyectan hacia el futuro. En la revisión de las publicaciones al respecto, se ha hecho una búsqueda profusa, con un mayor enfoque en el periodo comprendido entre el 2013 hasta la actualidad, buscando poner de manifiesto la constante evolución de la tecnología, pero sobre todo su inserción en los servicios financieros. Sin embargo, es importante señalar que en este campo las publicaciones se van incrementando, van cada vez más en aumento. Se han trazado, principalmente, tres objetivos que organizan la estructura del trabajo. En un primer momento, se busca determinar el alcance de lo que se entiende por tecnologías disruptivas y cómo estas se relacionan con las empresas y los negocios, por lo que se hará un breve repaso por su significado, sus inicios y evolución, así como un detalle de las principales tecnologías en nuestros días. En segundo lugar, se ha hecho una revisión de la estructura y la composición del sistema financiero tanto en América Latina como en el Perú. Finalmente, se ha investigado cómo las tecnologías disruptivas se están aplicando en el sistema financiero y los cambios que han originado. Las principales conclusiones que se desprenden de la investigación denotan que, al inicio, las primeras empresas en desarrollar tecnologías disruptivas en el sistema financiero fueron las fintech, por lo que hoy en día los sistemas financieros tradicionales las ven como una amenaza, implementando dentro de sus organizaciones unidades de innovación y aplicando estas metodologías ágiles para hacerles frente al emular sus actividades. Para algunos autores, de acuerdo con la tendencia global, la colaboración entre los bancos y las fintech es inevitable. Adicionalmente, se concluye que la regulación existente en las nuevas tecnologías generadas por los bancos y las fintech es escasa; de hecho, casi no existen en el Perú y se espera que se establezca una regulación para proteger a todos los actores del sistema en pro de su estabilidad y la prevención de actividades fraudulentas. Además, se concluye también en que no hay un desarrollo homogéneo en la aplicación de tecnologías disruptivas por todos los actores del sistema financiero, y tampoco existe consenso sobre los principales beneficios que las tecnologías disruptivas proporcionan a dicho sistema, pues mientras unos autores resaltan la contribución en términos de velocidad, tiempo y seguridad de información, para otros los beneficios radican en la reducción de costos y optimización de procesos. / The purpose of this research is to review the literature on the use of disruptive technologies in the financial sector and how they are projected into the future. In the review of the publications in this regard, a profuse search has been made, with a greater focus on the period from 2013 to the present, seeking to highlight the constant evolution of technology, but above all its insertion in services financial. However, it is important to note that in this field publications, they are increasing more and more. Mainly, three objectives have been outlined that organize the structure of the work. At first, we it seeks to determine the scope of what is understood by disruptive technologies and how these relationships with companies and businesses, so a brief review of their meaning, their beginnings and evolution, as well as a detail of the main technologies in our days. Second, a review was made of the structure and composition of the financial system in both Latin America and Peru. Finally, we have investigated how disruptive technologies are applying in the financial system and the changes they have caused. The main conclusions that emerge from the research show that, at the beginning, the first companies to develop disruptive technologies in the financial system were fintech companies, which is why today traditional financial systems see them as a threat, implementing innovation units within their organizations and applying these agile methodologies to face them by emulating their activities. For some authors, according to the global trend, collaboration between banks and fintech companies is inevitable. Furthermore, it is concluded that the existing regulation on new technologies generated by banks and fintech companies is scarce; in fact, they hardly exist in Peru and he hopes that a regulation will be established to protect all the actors in the system in favor of its stability and the prevention of fraudulent activities. In addition, it is also concluded that there is no homogeneous development in the application of disruptive technologies by all actors in the financial system, nor is there consensus on the main benefits that disruptive technologies controlled by said system, while other authors highlight the contribution in terms of speed, time and information security, for other benefits lie in reducing costs and optimizing processes. / Trabajo de Suficiencia Profesional

In recent years the development and implementation of AI and machine learning models has increased dramatically. The availability of quality data paving the way for sophisticated AI models. Financial institutions uses many models in their daily operations. They are however, heavily regulated and need to follow the regulation that are set by central banks auditory standard and the financial supervisory authorities. One of these standards is the disclosure of expected credit losses in financial statements of banks, called IFRS 9. Banks must measure the expected credit shortfall in line with regulations set up by the EBA and FSA. In this master thesis, we are collaborating with a Swedish bank to evaluate different machine learning models to predict defaults of a unsecured credit portfolio. The default probability is a key variable in the expected credit loss equation. The goal is not only to develop a valid model to predict these defaults but to create and evaluate different models based on their performance and transparency. With regulatory challenges within AI the need to introduce transparency in models are part of the process. When banks use models there’s a requirement on transparency which refers to of how easily a model can be understood with its architecture, calculations, feature importance and logic’s behind the decision making process. We have compared the commonly used model logistic regression to three machine learning models, decision tree, random forest and XG boost. Where we want to show the performance and transparency differences of the machine learning models and the industry standard. We have introduced a transparency evaluation tool called transparency matrix to shed light on the different transparency requirements of machine learning models. The results show that all of the tree based machine learning models are a better choice of algorithm when estimating defaults compared to the traditional logistic regression. This is shown in the AUC score as well as the R2 metric. We also show that when models increase in complexity there is a performance-transparency trade off, the more complex our models gets the better it makes predictions. / Under de senaste ̊aren har utvecklingen och implementeringen av AI- och maskininl ̈arningsmodeller o ̈kat dramatiskt. Tillg ̊angen till kvalitetsdata banar va ̈gen fo ̈r sofistikerade AI-modeller. Finansiella institutioner anva ̈nder m ̊anga modeller i sin dagliga verksamhet. De a ̈r dock starkt reglerade och m ̊aste fo ̈lja de regler som faststa ̈lls av centralbankernas revisionsstandard och finansiella tillsynsmyndigheter. En av dessa standarder a ̈r offentligg ̈orandet av fo ̈rva ̈ntade kreditfo ̈rluster i bankernas finansiella rapporter, kallad IFRS 9. Banker m ̊aste ma ̈ta den fo ̈rva ̈ntade kreditfo ̈rlusten i linje med regler som faststa ̈lls av EBA och FSA. I denna uppsats samarbetar vi med en svensk bank fo ̈r att utva ̈rdera olika maskininl ̈arningsmodeller f ̈or att fo ̈rutsa ̈ga fallisemang i en blankokreditsportfo ̈lj. Sannolikheten fo ̈r fallismang ̈ar en viktig variabel i ekvationen fo ̈r fo ̈rva ̈ntade kreditfo ̈rluster. M ̊alet a ̈r inte bara att utveckla en bra modell fo ̈r att prediktera fallismang, utan ocks ̊a att skapa och utva ̈rdera olika modeller baserat p ̊a deras prestanda och transparens. Med de utmaningar som finns inom AI a ̈r behovet av att info ̈ra transparens i modeller en del av processen. Na ̈r banker anva ̈nder modeller finns det krav p ̊a transparens som ha ̈nvisar till hur enkelt en modell kan fo ̈rst ̊as med sin arkitektur, bera ̈kningar, variabel p ̊averkan och logik bakom beslutsprocessen. Vi har ja ̈mfo ̈rt den vanligt anva ̈nda modellen logistisk regression med tre maskininla ̈rningsmodeller: Decision trees, Random forest och XG Boost. Vi vill visa skillnaderna i prestanda och transparens mellan maskininl ̈arningsmodeller och branschstandarden. Vi har introducerat ett verktyg fo ̈r transparensutva ̈rdering som kallas transparensmatris fo ̈r att belysa de olika transparenskraven fo ̈r maskininla ̈rningsmodeller. Resultaten visar att alla tra ̈d-baserade maskininla ̈rningsmodeller a ̈r ett ba ̈ttre val av modell vid prediktion av fallisemang j ̈amfo ̈rt med den traditionella logistiska regressionen. Detta visas i AUC-score samt R2 va ̈rdet. Vi visar ocks ̊a att n ̈ar modeller blir mer komplexa uppst ̊ar en kompromiss mellan prestanda och transparens; ju mer komplexa v ̊ara modeller blir, desto ba ̈ttre blir deras prediktioner.