In recent years, we have witnessed a massive increase in the number of startups, which are also producing significant amounts of digital data. This poses a new challenge for expert analysts due to their limited attention spans and knowledge, also considering the low success rate of empirical startup evaluation. However, this new era also presents a great opportunity for the application of artificial intelligence (AI) towards intelligent startup investments. There are only a few works that have considered the potential of AI for startup recommendation, and they have not paid attention to the actual requirements of investors, also neglecting to investigate the desirability, feasibility, and value proposition of this venture. In this paper, we answer these questions by conducting a survey in collaboration with three major organizations of the Greek startup ecosystem. Furthermore, this paper also presents the design specifications for an AI-based decision support system for forecasting startup sustainability that is aligned with the requirements of expert analysts. Preliminary experiments with 44 Greek startups demonstrate Random Forest’s strong ability to predict sustainability scores.
Portfolio management (PM) facilitates optimal investing decisions and enables organizations to control risks and achieve stable financial growth. Advances in machine learning, mostly through supervised learning, are drastically changing the way in which PM is conducted. More recently, unsupervised learning is also emerging as a paradigm that can support the creation of diversified and profitable portfolios through stock clustering. In the corresponding literature, there is significant evidence that cluster-informed methods can outperform both traditional and supervised approaches to PM. However, these works are few and have not considered state-of-the-art deep learning approaches for clustering, while stock allocation is often limited to equally weighted portfolios or mean-variance optimization (MVO). To address these issues, we propose a cluster-informed PM method based on deep temporal clustering (DTC) along with our recommended parameters for training convergence, combined with the conditional drawdown at risk (CDaR) portfolio allocation method. Unlike MVO, CDaR considers tail risk and can minimize extreme price drawdowns. Cluster validity metrics reveal that DTC outperforms previously proposed stock clustering methods. Furthermore, DTC enhanced by CDaR achieves a higher expected Sortino ratio (1.1) compared to previous works in clustering-based PM. Additional Brinson attribution and maximum drawdown analyses further confirm the robustness of our method.