Lauri Nevasalmi’s research while affiliated with University of Turku and other places

What is this page?

This page lists works of an author who doesn't have a ResearchGate profile or hasn't added the works to their profile yet. It is automatically generated from public (personal) data to further our legitimate goal of comprehensive and accurate scientific recordkeeping. If you are this author and want this page removed, please let us know.

Publications (5)

Recession forecasting with high‐dimensional data†
  • Article
  • Full-text available

September 2021

·

104 Reads

·

4 Citations

Lauri Nevasalmi

In this paper, a large amount of different financial and macroeconomic variables are used to predict the U.S. recession periods. We propose a new cost‐sensitive extension to the gradient boosting model which can take into account the class imbalance problem of the binary response variable. The class imbalance, caused by the scarcity of recession periods in our application, is a problem that is emphasized with high‐dimensional datasets. Our empirical results show that the introduced cost‐sensitive extension outperforms the traditional gradient boosting model in both in‐sample and out‐of‐sample forecasting. Among the large set of candidate predictors, different types of interest rate spreads turn out to be the most important predictors when forecasting U.S. recession periods.

Download
Fig. 1. k-Nearest neighbor classification.
Fig. 2. 4-terminal node regression tree.
Fig. 3. Artificial neural network.
Fig. 4. Support vector machine.
Fig. 6. Trading simulation results for each method.

+3

Forecasting multinomial stock returns using machine learning methods

November 2020

·

444 Reads

·

27 Citations

The Journal of Finance and Data Science

Lauri Nevasalmi

In this paper, the daily returns of the S&P 500 stock market index are predicted using a variety of different machine learning methods. We propose a new multinomial classification approach to forecasting stock returns. The multinomial approach can isolate the noisy fluctuation around zero return and allows us to focus on predicting the more informative large absolute returns. Our in-sample and out-of-sample forecasting results indicate significant return predictability from a statistical point of view. Moreover, all the machine learning methods considered outperform the benchmark buy-and-hold strategy in a real-life trading simulation. The gradient boosting machine is the top-performer in terms of both the statistical and economic evaluation criteria.

Download

Citations (4)

... Complementing this research, Choi et al. [44] employ the yield curve, including the yield spread between 10-year and 3-month Treasury bonds, to predict recession probabilities using machine learning algorithms. Similarly, Nevasalmi [45] utilize the Gradient Boosting model to forecast recession periods in the United States, incorporating macroeconomic and financial variables as predictors, with a particular focus on the predictive power of interest rate differentials. This study highlights that machine learning techniques substantially enhance recession prediction performance, illustrating their effectiveness in the economic context. ...

Reference:

Machine Learning Insights into Bolivia's Economic Downturns
Recession forecasting with high‐dimensional data†
Lauri Nevasalmi

... In this study, we extend this approach by adopting a threshold, inspired by the work of Nevasalmi (2020). Rather than simply distinguishing between positive and negative returns, we introduce a finer classification that isolates some of the noise and better identifies extreme returns, whether strongly positive or negative. ...

Reference:

Bridging Econometrics and AI: VaR Estimation via Reinforcement Learning and GARCH Models
Forecasting multinomial stock returns using machine learning methods

The Journal of Finance and Data Science

Lauri Nevasalmi

... Он представляет собой индекс волатильности, указывающий на ожидания фондового рынка относительно краткосрочных изменений (в течение 30 дней) индекса S&P500 [1,2]. Индекс считается единственным наиболее влиятельным предиктором доходности акций на следующий день [3]. Для моделирования VIX учитываются скачки цен инвестиционных активов, их волатильность и позиции трейдеров на фьючерсном рынке VIX, используется модель типа Хестона, представляющая собой хорошую основу для воссоздания ценообразования фьючерсов VIX [4]. ...

Reference:

THE DURATION OF THE IMPACT OF THE “INVESTOR FEAR INDEX” ON THE RUSSIAN STOCK MARKET
Forecasting Multinomial Stock Returns Using Machine Learning Methods
  • Citing Article

  • January 2020

SSRN Electronic Journal

Lauri Nevasalmi

... These include parametric portfolio policies (Brandt et al., 2009;DeMiguel et al., 2020), a boosting approach (Nevasalmi and Nyberg, 2021), a subset combination approach (Maasoumi et al., 2022), a genetic programming approach (Liu and Zhou, 2024), and an approach that using deep reinforcement learning (Cong et al., 2024). The above mentioned techniques involve optimizing economic utility for specific portfolio choice problems at the individual asset level, while our approach is about maximizing utility one level up by combining PRs. ...

Reference:

Ensembles of Portfolio Rules
Moving Forward from Predictive Regressions: Boosting Asset Allocation Decisions
  • Citing Article

  • January 2020

SSRN Electronic Journal

Lauri Nevasalmi

·

Henri Nyberg