Afterlunch webinar Zihao Liu – Deep learning for pension communication – a road map

Netspar organizes this After Lunch Webinar for partners and employees of partners. Researchers will outline their latest retirement research and then receive feedback and answer questions. It is just another way we bring science, academics, and professional practice closer together.

In this After Lunch Webinar, Zihao Liu (Tilburg University) explains more about the research: Deep learning for pension communication – a road map

This research is being conducted in conjunction with Peter de Goeij (TiU), and Eric Postma (TiU)

Questions and input on this ongoing research are most welcome.

This event will be in English.

In this paper, we propose to apply artificial intelligence (AI) in pension communication.

We first offer a short literature review on channels of pension communication and discuss potential areas for improvement in verbal and non-verbal communication.

Secondly, we show empirical examples of how deep learning (DL) can be helpful in terms of understanding the effectiveness of communication. We apply tailored DL models for analyzing CEO voiceprints of earning conference calls with analysts to predict the firm’s future performance measured by analyst recommendation changes, unexpected earnings, and cumulative abnormal returns. Using an out-of-sample evaluation (which is standard in AI), we show examples of how communicated firm information can affect a firm’s market perception.

Finally, we will propose a roadmap for applying DL models once the audio datasets are available under a pension communication setting.

Locatie: Tilburg University Seminar Room K834 Warandelan 2 5037 AB Tilburg

Netspar, Network for Studies on Pensions, Aging and Retirement, is een denktank en kennisnetwerk. Netspar is gericht op een goed geïnformeerd pensioendebat.


Missie en strategie           •           Netwerk           •           Organisatie           •          Podcasts
Board Brief            •            Werkprogramma 2023-2027           •           Onderzoeksagenda


Onze partners

B20160708_universiteit utrecht
B20210909_SPMS_logo download greyscale smaller
Bekijk al onze partners