arXiv subjects

Sergei Seleznev

Publications and source records attributed to Sergei Seleznev.

3 recordsLinked to original sources

arXiv2026

Fake Date Tests: Can We Trust In-sample Accuracy of LLMs in Macroeconomic Forecasting?

Large language models (LLMs) are a type of machine learning tool that economists have started to apply in their empirical research. One such application is macroeconomic forecasting with backtesting of LLMs, even though they are trained on the same data that is used to estimate their forecasting performance. Can these in-sample accuracy results be extrapolated to the model's out-of-sample performance? To answer this question, we developed a family of prompt sensitivity tests and two members of this family, which we call the fake date tests. These tests aim to detect two types of biases in LLMs' in-sample forecasts: lookahead bias and context bias. According to the empirical results, none of the modern LLMs tested in this study passed our first test, signaling the presence of lookahead bias in their in-sample forecasts.

econ.EM↗

arXiv2023

Amortized neural networks for agent-based model forecasting

In this paper, we propose a new procedure for unconditional and conditional forecasting in agent-based models. The proposed algorithm is based on the application of amortized neural networks and consists of two steps. The first step simulates artificial datasets from the model. In the second step, a neural network is trained to predict the future values of the variables using the history of observations. The main advantage of the proposed algorithm is its speed. This is due to the fact that, after the training procedure, it can be used to yield predictions for almost any data without additional simulations or the re-estimation of the neural network

econ.EM↗

arXiv2022

Fast Estimation of Bayesian State Space Models Using Amortized Simulation-Based Inference

This paper presents a fast algorithm for estimating hidden states of Bayesian state space models. The algorithm is a variation of amortized simulation-based inference algorithms, where a large number of artificial datasets are generated at the first stage, and then a flexible model is trained to predict the variables of interest. In contrast to those proposed earlier, the procedure described in this paper makes it possible to train estimators for hidden states by concentrating only on certain characteristics of the marginal posterior distributions and introducing inductive bias. Illustrations using the examples of the stochastic volatility model, nonlinear dynamic stochastic general equilibrium model, and seasonal adjustment procedure with breaks in seasonality show that the algorithm has sufficient accuracy for practical use. Moreover, after pretraining, which takes several hours, finding the posterior distribution for any dataset takes from hundredths to tenths of a second.

econ.EM↗