Internship Topics

Prof. Helmut Prendinger

Thank you for your interest in our topics!

Objective:

The Objective of the Internship is a tangible result, such as:

· Research results that stand a chance of publication in a major venue (journal or conference), whereby the Intern assumes authorship or co-authorship

· Development or co-development of competitive software, or an intelligent system that can be demonstrated

Paper writing will be supported by Prendinger Lab.

Topic 1:

Research Area: Generative AI

Title of Research Topic: LLMs and LMMs for Stock/Crypto Market Prediction

We investigate the potential of Large Language Models (LLMs) and Large Multimodal Models (LMMs), such as GPT-4o, for predicting the price action of stocks and crypto assets as a basic component for swing trading. The success of LLMs in natural language applications and vision tasks is already clearly understood (e.g., Chat-GPT). A very recent development is to prompt an LLM with both text and time series data, or even images, such as technical price charts (in case of LMMs).

Our goal is to study LLMs and LMMs for price forecasting of financial instruments. We focus on tuning based predictors (e.g., Time-LLM), and also consider neuro-symbolic AI.

Github: https://github.com/qingsongedu/Awesome-TimeSeries-SpatioTemporal-LM-LLM

Besides price action (closing prices of some asset class), we consider technical analysis (chart analysis), market sentiment, and other relevant factors for accurately predicting the market.

Forecasting the market is more than applying available time series models to financial assets. Our experience shows that we also need to study methods and techniques developed in AI for Finance (de Prado, 2018). Finally, interest in price action of financial assets is important to enjoy this topic.

Key references:

Owen Chaffard, Marc Cavazza, Helmut Prendinger, Enhancing Large Language Models for Bitcoin time series forecasting, Knowledge-Based Systems, 2024.10, submitted

Ming Jin, Yifan Zhang, Wei Chen, Kexin Zhang, Yuxuan Liang, Bin Yang, Jindong Wang, Shirui Pan, Qingsong Wen, Position Paper: What Can Large Language Models Tell Us about Time Series Analysis, 2024.6,

https://arxiv.org/abs/2402.02713

M. Jin, S. Wang, L. Ma, Z. Chu, J. Y. Zhang, X. Shi, P.-Y. Chen, Y. Liang, Y.-F. Li, S. Pan, Q. Wen, TIME-LLM: Time Series Forecasting by Reprogramming Large Language Models, 2024.2, ICLR 2024,

https://arxiv.org/pdf/2310.01728.pdf

Zhengyuan Yang, Linjie Li, Kevin Lin, Jianfeng Wang, Chung-Ching Lin, Zicheng Liu, Lijuan Wang, The Dawn of LMMs: Preliminary Explorations with GPT-4V(ision), 2023.10, https://arxiv.org/abs/2309.17421

M. Lopez de Prado, Advances in Financial Machine Learning, Wiley, 2018

Topic 2:

Research Area: Generative AI

Title of Research Topic: Time Series Foundation Models for Stock/Crypto Market Prediction

We investigate time series foundation models for predicting the price action of stocks and crypto assets as a basic component for swing trading. A foundation model for time series data is a model that has been pre-trained on a large and diverse set of time series data, or even text data. Our goal is to test time series foundation models (e.g., Chronos) for price forecasting of financial instruments.

Github: https://github.com/qingsongedu/Awesome-TimeSeries-SpatioTemporal-LM-LLM

Besides price action (closing prices of some asset class), we consider technical analysis (chart analysis), market sentiment, and other relevant factors for accurately predicting the market.

Forecasting the market is more than applying available time series models to financial assets. Our experience shows that we also need to study methods and techniques developed in AI for Finance (de Prado, 2018). Finally, interest in price action of financial assets is important to enjoy this topic.

Key references:

Owen Chaffard, Marc Cavazza, Helmut Prendinger, Enhancing Large Language Models for Bitcoin time series forecasting, Knowledge-Based Systems, 2024.10, submitted

Abdul Fatir Ansari, Lorenzo Stella, Caner Turkmen, Xiyuan Zhang, Pedro Mercado, Huibin Shen, Oleksandr Shchur, Syama Sundar Rangapuram, Sebastian Pineda Arango, Shubham Kapoor, Jasper Zschiegner, Danielle C. Maddix, Michael W. Mahoney, Kari Torkkola, Andrew Gordon Wilson, Michael Bohlke-Schneider, Yuyang Wang, Chronos: Learning the Language of Time Series, 2024.3, https://arxiv.org/abs/2403.07815

M. Jin, S. Wang, L. Ma, Z. Chu, J. Y. Zhang, X. Shi, P.-Y. Chen, Y. Liang, Y.-F. Li, S. Pan, Q. Wen, TIME-LLM: Time Series Forecasting by Reprogramming Large Language Models, 2024.2, ICLR 2024,

https://arxiv.org/pdf/2310.01728.pdf

M. Lopez de Prado, Advances in Financial Machine Learning, Wiley, 2018

Topic 3:

Research Area: Token Economy, Crypto Token, Smart Contract

Title of Research Topic: Market Design for Advanced Air Mobility (drones and “flying cars”)

We have developed a prototype of a complete distributed advanced air mobility (AAM) system to safely coordinate drones and “flying cars”, and conducted related simulation studies.

· Video: https://youtu.be/QuIEdMqFJqw

We investigate market design for AAM, based on ideas from token economy (Web3). Our studies include:

· Development of a AAM related crypto token

· Use of blockchain in an AAM simulator

· Use of cryptography and Zero-Knowledge Proofs (ZKPs)

· Development of Smart Contracts with Solidity

· Use of Generative AI (LLMs) to create Smart Contracts

Key references:

Sven Seuken, Paul Friedrich, Ludwig Dierks, Market design for drone traffic management. AAAI, 2022, https://ojs.aaai.org/index.php/AAAI/article/view/21493

Shermin Voshmgir, Token Economy. How the Web3 reinvents the Internet, Second Edition, 2020, https://github.com/sherminvo/TokenEconomyBook

Contact

E-mail: helmut @ nii [Address format is: username@nii.ac.jp]

Personal Website: http://research.nii.ac.jp/~prendinger/

LOOKING FORWARD TO HEARING FROM YOU!