Power Derivatives Market Trend Prediction with Machine Learning and Technical Analysis - Bachelor’s Thesis

Aug 3, 2026

The thesis develops a machine learning model to predict the short-term direction of power derivatives prices using technical analysis signals. The approach is built on Gradient Boosting and implemented in Python with LightGBM. Training data comes from daily Nordic system price futures open, close, high, and low values from 27.11.2017–3.4.2023, labeled into a five-class scale (strong sell to strong buy). Results are modest: the model outperforms a random baseline but remains similar to a naive prior-day trend model, and technical indicators contribute limited incremental value. Limited data availability suggests that expanding the dataset and further model development are needed for practical trading use.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages26

Reading Time1 h 6 min

AccessFree to download

1. Introduction

2. Electricity Markets

2.1 Spot market

2.2 Derivatives market

3. Methods

3.1 Machine learning

3.2 Technical analysis

3.3 Gradient boosting and LightGBM

4. Data

4.1 Properties

4.2 Splitting the data

4.3 Labelling of data

4.4 Preprocessing of data

5. Experiments

5.1 Naive model

5.2 Results

6. Conclusions

References

Taneli Liedes POWER DERIVATIVES MARKET TREND PREDICTION WITH MACHINE LEARNING AND TECHNICAL ANALYSIS Bachelor’s Thesis Faculty of Information Technology and Communication Sciences Examiner: Juho Kanniainen May 2023 ABSTRACT Taneli Liedes: Power Derivatives Market Trend Prediction with Machine Learning and Technical Analysis Bachelor’s Thesis Tampere University Bachelor’s Degree Program in Information Technology May 2023 The objective of this thesis was to develop a machine learning model that predicts the shortterm direction of power derivatives price by utilizing technical analysis. The use of machine learning in predicting the price and trend of various financial products has been studied widely. The developed machine learning model is based on the Gradient Boosting method, which is a popular machine learning method , which is one of the best models for multi-class classification tasks per studies. The data used was daily open, close, high, and low prices of the Nordic system price future from timespan 27.11.2017-3.4.2023. The source of the data was Nasdaq OMX Commodities. The model was developed in Python, using LightGBM as framework. The model predicts the trend of derivatives in the selected timespan. The lengths of the tested timespans ranged from two to eight days, but this is not of essential importance in terms of the model's operation, longer timespans could also be used. The model predicts the trend on a five-step scale named as follows; strong sell, sell, hold, buy and strong buy. It was trained in such a way that a class was assigned for each day in the training data , based on how much the price increased or decreased during the selected timespan. The highest and lowest price of each day in the timespan were used as a benchmark for the closing price of that day. The thresholds which determine the class are parameters of the model, the magnitude of which is easy to modify. The results were not particularly good, but still better than a random number generator. The naive model, which predicted the same trend as the previous day , achieved similar results to the developed machine learning model. The indicators based on technical analysis also did not affect the predictions made by the model significantly , contrary to what was assumed. On the other hand, there was a limited amount of data available, increasing the amount of training data might improve the accuracy of the model. The model needs to be further developed so that it could be used as a proper aid in trading power derivatives. Keywords: electricity markets, power derivatives, power trading, gradient boosting, market trend prediction, technical analysis , machine learning SISÄLLYSLUETTELO 1. INTRODUCTION .................................................................................................. 1 2. ELECTRICITY MARKETS..................................................................................... 2 2.1 Spot market ......................................................................................... 2 2.2 Derivatives market ............................................................................... 3 3. METHODS ............................................................................................................ 5 3.1 Machine learning.................................................................................. 5 3.2 Technical analysis................................................................................ 5 3.3 Gradient boosting and LightGBM ......................................................... 7 4. DATA .................................................................................................................. 10 4.1 Properties .......................................................................................... 10 4.2 Splitting the data ................................................................................ 10 4.3 Labelling of data.............

FAQs

What is the main objective of the thesis?

To examine whether machine learning can be used for power derivatives market trend prediction with support from technical analysis, focusing on short-term price direction.

Which data source and features are used to train the model?

Daily open, close, high, and low prices of Nordic system price futures are used, sourced from Nasdaq OMX Commodities for 27.11.2017–3.4.2023.

How does the model represent market direction and what algorithm is used?

The model predicts trends on a five-step scale (strong sell, sell, hold, buy, strong buy) using Gradient Boosting decision trees implemented with LightGBM.

Aug 3, 2026

Upload by Ava Thompson