Autoregressive Models

Extrapolating the long-term seasonal component of electricity prices for forecasting in the day-ahead market ArXiv ID: 2503.02518 “View on arXiv” Authors: Unknown Abstract Recent studies provide evidence that decomposing the electricity price into the long-term seasonal component (LTSC) and the remaining part, predicting both separately, and then combining their forecasts can bring significant accuracy gains in day-ahead electricity price forecasting. However, not much attention has been paid to predicting the LTSC, and the last 24 hourly values of the estimated pattern are typically copied for the target day. To address this gap, we introduce a novel approach which extracts the trend-seasonal pattern from a price series extrapolated using price forecasts for the next 24 hours. We assess it using two 5-year long test periods from the German and Spanish power markets, covering the Covid-19 pandemic, the 2021/2022 energy crisis, and the war in Ukraine. Considering parsimonious autoregressive and LASSO-estimated models, we find that improvements in predictive accuracy range from 3% to 15% in terms of the root mean squared error and exceed 1% in terms of profits from a realistic trading strategy involving day-ahead bidding and battery storage. ...

A Comparison of Cryptocurrency Volatility-benchmarking New and Mature Asset Classes ArXiv ID: 2404.04962 “View on arXiv” Authors: Unknown Abstract The paper analyzes the cryptocurrency ecosystem at both the aggregate and individual levels to understand the factors that impact future volatility. The study uses high-frequency panel data from 2020 to 2022 to examine the relationship between several market volatility drivers, such as daily leverage, signed volatility and jumps. Several known autoregressive model specifications are estimated over different market regimes, and results are compared to equity data as a reference benchmark of a more mature asset class. The panel estimations show that the positive market returns at the high-frequency level increase price volatility, contrary to what is expected from the classical financial literature. We attributed this effect to the price dynamics over the last year of the dataset (2022) by repeating the estimation on different time spans. Moreover, the positive signed volatility and negative daily leverage positively impact the cryptocurrencies’ future volatility, unlike what emerges from the same study on a cross-section of stocks. This result signals a structural difference in a nascent cryptocurrency market that has to mature yet. Further individual-level analysis confirms the findings of the panel analysis and highlights that these effects are statistically significant and commonly shared among many components in the selected universe. ...

Liquidity Jump, Liquidity Diffusion, and Treatment on Wash Trading of Crypto Assets ArXiv ID: 2404.07222 “View on arXiv” Authors: Unknown Abstract We propose that the liquidity of an asset includes two components: liquidity jump and liquidity diffusion. We show that liquidity diffusion has a higher correlation with crypto wash trading than liquidity jump and demonstrate that treatment on wash trading significantly reduces the level of liquidity diffusion, but only marginally reduces that of liquidity jump. We confirm that the autoregressive models are highly effective in modeling the liquidity-adjusted return with and without the treatment on wash trading. We argue that treatment on wash trading is unnecessary in modeling established crypto assets that trade in unregulated but mainstream exchanges. ...

Generative AI for End-to-End Limit Order Book Modelling: A Token-Level Autoregressive Generative Model of Message Flow Using a Deep State Space Network ArXiv ID: 2309.00638 “View on arXiv” Authors: Unknown Abstract Developing a generative model of realistic order flow in financial markets is a challenging open problem, with numerous applications for market participants. Addressing this, we propose the first end-to-end autoregressive generative model that generates tokenized limit order book (LOB) messages. These messages are interpreted by a Jax-LOB simulator, which updates the LOB state. To handle long sequences efficiently, the model employs simplified structured state-space layers to process sequences of order book states and tokenized messages. Using LOBSTER data of NASDAQ equity LOBs, we develop a custom tokenizer for message data, converting groups of successive digits to tokens, similar to tokenization in large language models. Out-of-sample results show promising performance in approximating the data distribution, as evidenced by low model perplexity. Furthermore, the mid-price returns calculated from the generated order flow exhibit a significant correlation with the data, indicating impressive conditional forecast performance. Due to the granularity of generated data, and the accuracy of the model, it offers new application areas for future work beyond forecasting, e.g. acting as a world model in high-frequency financial reinforcement learning applications. Overall, our results invite the use and extension of the model in the direction of autoregressive large financial models for the generation of high-frequency financial data and we commit to open-sourcing our code to facilitate future research. ...

Causality between investor sentiment and the shares return on the Moroccan and Tunisian financial markets ArXiv ID: 2305.16632 “View on arXiv” Authors: Unknown Abstract This paper aims to test the relationship between investor sentiment and the profitability of stocks listed on two emergent financial markets, the Moroccan and Tunisian ones. Two indirect measures of investor sentiment are used, SENT and ARMS. These sentiment indicators show that there is an important relationship between the stocks returns and investor sentiment. Indeed, the results of modeling investor sentiment by past observations show that sentiment has weak memory; on the other hand, series of changes in sentiment have significant memory. The results of the Granger causality test between stock return and investor sentiment show us that profitability causes investor sentiment and not the other way around for the two financial markets studied.Thanks to four autoregressive relationships estimated between investor sentiment, change in sentiment, stock return and change in stock return, we find firstly that the returns predict the changes in sentiments which confirms with our hypothesis and secondly, the variation in profitability negatively affects investor sentiment.We conclude that whatever sentiment measure is used there is a positive and significant relationship between investor sentiment and profitability, but sentiment cannot be predicted from our various variables. ...