The role of AI in capital structure to enhance corporate funding strategies

Abstract

The purpose of this study was to assess if Artificial Intelligence (AI) could be used in the Capital Asset Pricing Model (CAPM) and whether the use of AI could bring a more accurate estimation of expected returns. Cost of capital defines the minimum return expected from any investment made by a firm. Hence for managers to maximise the value of the corporation, it is essential to have an accurate estimation of the cost of capital. For the purpose of analysing securities, the adjusted closing stock prices of 10 high-tech public companies were studied from January 2013 to January 2019. This research assumed that there is a need to predict returns for the next year. Hence one year of historical data was used to calculate traditional CAPM value and also train the Recurrent Neural Networks (RNN) to predict stock prices of the upcoming year. A generic deep learning network architecture was developed with the use of Long Short Term Memory (LSTM) and dropout layers. After calculating the returns using traditional and AI approaches, two methods for calculation of CAPM were proposed and compared. Following the analysis, it was found that the use of AI improved the accuracy of cost of equity estimations by over 60%. The strong ability of the selected deep learning neural network to predict stock prices, increased the accuracy of estimating returns by at least 18%. This study concluded that AI has significant potentials to replace traditional asset pricing models in the near future.

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 34 citations exist upstream.

Papers that cite the same references — the relational fallback while embeddings are still backfilling.