TF-CoDiT: Conditional Time Series Synthesis with Diffusion Transformers for Treasury Futures

TL;DR

This paper introduces TF-CoDiT, a novel diffusion transformer framework for synthesizing treasury futures data, addressing unique market challenges with wavelet transforms and a hierarchical VAE, achieving high fidelity and robustness.

Contribution

TF-CoDiT is the first DiT framework tailored for treasury futures synthesis, incorporating DWT, a hierarchical VAE, and FinMAP for condition encoding, enabling effective low-data learning.

Findings

High-quality data synthesis with errors below 0.433 (MSE) and 0.453 (MAE).

Robust performance across different contracts and time horizons.

Effective modeling of treasury futures' market dependencies and correlations.

Abstract

Diffusion Transformers (DiT) have achieved milestones in synthesizing financial time-series data, such as stock prices and order flows. However, their performance in synthesizing treasury futures data is still underexplored. This work emphasizes the characteristics of treasury futures data, including its low volume, market dependencies, and the grouped correlations among multivariables. To overcome these challenges, we propose TF-CoDiT, the first DiT framework for language-controlled treasury futures synthesis. To facilitate low-data learning, TF-CoDiT adapts the standard DiT by transforming multi-channel 1-D time series into Discrete Wavelet Transform (DWT) coefficient matrices. A U-shape VAE is proposed to encode cross-channel dependencies hierarchically into a latent variable and bridge the latent and DWT spaces through decoding, thereby enabling latent diffusion generation. To derive prompts that cover essential conditions, we introduce the Financial Market Attribute Protocol (FinMAP) - a multi-level description system that standardizes daily$/$periodical market dynamics by recognizing 17$/$23 economic indicators from 7/8 perspectives. In our experiments, we gather four types of treasury futures data covering the period from 2015 to 2025, and define data synthesis tasks with durations ranging from one week to four months. Extensive evaluations demonstrate that TF-CoDiT can produce highly authentic data with errors at most 0.433 (MSE) and 0.453 (MAE) to the ground-truth. Further studies evidence the robustness of TF-CoDiT across contracts and temporal horizons.