Innovative Technology at the Interface of Finance and Operations

Although there are many versions of blockchain technology today, it was first introduced in 2008 as the technology supporting Bitcoin, the first successful virtual currency system. Yet in and of itself, blockchain technology is much more than the underpinning for Bitcoin (and other cryptocurrencies) and has found many applications beyond its initial purpose. The goal of this advanced primer is to review the current state of this technology and to discuss some of its advantages and drawbacks in settings beyond cryptocurrencies.

The control of self-organizing systems of autonomous machines (e.g., roadway vehicles and drones) need not mimic the legacy human-centric systems they are poised to replace. In fact, new operational paradigms based on transactionalizing episodic multi-machine interactions may have the potential to resolve key legacy issues linking system financial self-sustainment and efficient operations. This chapter discusses the fundamentals of machine negotiation over shared space and considers the interplay between earned trust and priority that is critical to the integrity of collective maneuver planning. Collective maneuver planning is systematized into an iterative process that includes conflict identification, negotiation, and priority determination and, when complete, transformed into a multi-machine transaction. The power of the multi-machine maneuver transaction is examined in more detail to align operational and financial policies considering the full self-organizing ecosystem including the role of supporting infrastructure.

We present two tutorials: (1) a finance tutorial for OM researchers and (2) an OM tutorial for finance researchers. We complement textbook treatment of important ideas from one discipline with examples of applications to the other discipline. Our goal is to lower the entry cost for new researchers interested in problems at the interface of the two disciplines.

The nature of payment systems is changing. In recent times, traditional financial institutions have provided the majority of payment services. Over the centuries, incumbent banks developed a reputation to act as trusted brokers. This is their main advantage today, yet we consider several scenarios for the future of payments, all of which entail a new basis of competition and a new locus of trust. While trust will be just as important in the future as in the past, the meaning of trust is changing fast. In a world of instant payments, universal connectivity between payment networks, and perhaps even central-bank accounts for ordinary citizens to keep their digital funds, the role of banks could be quite different than it has been for the last centuries.

Machine learning is revolutionizing healthcare management due to the exponential increase in health records’ digitization and computing power. Predictive analytics are utilized across multiple applications and different hospital departments to accelerate workflow and improve medical decision-making. Machine learning is decisively altering diagnostic processes such as imaging, as computer vision continues to be adopted in radiology. In this chapter we highlight some of the many machine learning applications with direct impact on operations and/or financial outcomes within a hospital setting. We also address the important topics of fairness and transparency in healthcare modeling.

The field of operations management has witnessed a fast-growing trend of data analytics in recent years. In particular, spurred by the increasing availability of data and methodological advancement in machine learning, a large body of recent literature in this field takes advantage of machine learning techniques for analyzing how firms should operate. In this chapter, we review applications of different machine learning methods, including supervised learning, unsupervised learning, and reinforcement learning, in various areas of operations management. We highlight how both supervised and unsupervised learning shape operations management research in both descriptive and prescriptive analyses. We also emphasize how different variants of reinforcement learning are applied in diverse operational decision problems. We then identify several exciting future directions at the intersection of machine learning and operations management.

Fraud exists in all walks of life and detecting and preventing fraud represents an important research question relevant to many stakeholders in society. With the rise in big data and artificial intelligence, new opportunities have arisen in using advanced machine learning models to detect fraud. This chapter provides a comprehensive overview of the challenges in detecting fraud using machine learning. We use a framework (data, method, and evaluation criterion) to review some of the practical considerations that may affect the implementation of machine-learning models to predict fraud. Then, we review select papers in the academic literature across different disciplines that can help address some of the fraud detection challenges. Finally, we suggest promising future directions for this line of research. As accounting fraud constitutes an important class of fraud, we will discuss all of these issues within the context of accounting fraud detection.

This paper focuses broadly on the application of various types of AI technology in the buy-side of financial services and more specifically on the application of AI to financial portfolio management. Current market volatility in response to the COVID-19 pandemic has given new urgency to the perennial challenge of achieving quality investment returns, and the ever-present trade-off between return and risk that all portfolio managers have to master. The complexity and volume of relevant information today, and the rate of change in the current environment, have only heightened the need for smarter financial choices. Various types of AI may be used to respectively achieve higher portfolio returns, increase operational efficiency, and enhance the customer experience. Successful AI usage will always involve an optimum mix of machine-provided and human-based services, where the AI enhances and accelerates human portfolio decision-making and saves labor costs.

This chapter develops a novel approach to predict post-money valuation of startups across various regions and sectors, as well as their probabilities of success. Using startup funding data and descriptions from Crunchbase over a 10-year period, we develop two models linking information such as description, region, and venture capital funding to successful outcomes such as the achievement of an acquisition or IPO. The first model utilizes latent Dirichlet allocation, a generative statistical model in natural language processing, to organize the startups in the dataset into clusters representing various sectors in the typical economy. A distributed gradient boosting regressor (XGBoost) with hyperparameters optimized through Bayesian optimization is subsequently deployed to make use of the resultant feature set to predict post-money valuation. Our model consistently achieves an accuracy of over 95% on hold-out test sets, even with some continuous features removed. The second model is a feed-forward neural network constructed using TensorFlow, with the final layer providing predicted probabilities of success. We find that post-money valuations across regions are typically log-normally distributed, and startups in regions such as San Francisco Bay Area typically witness higher valuations across most sectors. We also find that startups operating in specific geographical regions and sectors of economy (e.g., regions and sectors with higher number of investors) typically have higher predicted probabilities of success. Our approach offers an empirical perspective to startups, policymakers, and venture funds to benchmark and predict valuation and success, clearing some opacity in the modern startup economy.