Financial Times Series Forecasting of Clustered Stocks

Affonso, Felipe; Dias, Thiago Magela Rodrigues; Pinto, Adílson Luiz

doi:10.1007/s11036-020-01647-8

Cited by 7 publications

(5 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This chapter's literature underscores various applications of clustering within finance, notably in portfolio formation. As previous studies indicate, the k-means algorithm has demonstrated robust performance in stock selection (Affonso et al, 2021;Bini and Mathew, 2016;Nanda et al, 2010).…”

Section: Literature Reviewmentioning

confidence: 78%

See 1 more Smart Citation

Clustering-based value investing strategy in the Helsinki Stock Exchange: k-means algorithm

Issakainen

2023

JIBE

View full text Add to dashboard Cite

The purpose of this research is to study the possibility of combining quantitative clustering of stocks and value investing. The feasibility of this approach is tested using Finnish market data from the period 2005 to 2021. The benchmark index used in this research is the OMX Helsinki Growth Index. The strategy is based on the combination of P/E, P/CF, and P/B ratios, which serve as the basis for the k-means algorithm. The data is pre-processed by removing stocks that have not generated positive earnings and cash flow during the previous 12 months. The k-means algorithm assigns stocks to clusters, and the cluster with the lowest financial ratios is chosen as the value portfolio. The research also includes a sensitivity analysis of value portfolios, where the initial number of clusters in the clustering phase ranges from three to ten. Returns of different value portfolios are compared to each other and the benchmark index. The quality of results is evaluated using the Sharpe ratio and Jensen's alpha. According to the findings, the value portfolio constructed using nine clusters generated the highest risk-adjusted return, with an annual return of 30.27% over the 2005 to 2021 period. Furthermore, the best-performing value portfolio from 2005 to 2017 was compared to the benchmark index from 2018 to 2021. The value portfolio achieved an annual return of 26.05% during the 2018-2021 period, while the corresponding return of the benchmark index was 11.74%.

show abstract

Section: Literature Reviewmentioning

confidence: 78%

“…Results indicated that employing the k-means algorithm did not compromise prediction accuracy. The authors concluded that leveraging the k-means clustering approach enables investors to economize time by reducing manual screening efforts for similar stocks (Affonso et al, 2021).…”

Section: Literature Reviewmentioning

confidence: 99%

Clustering-based value investing strategy in the Helsinki Stock Exchange: k-means algorithm

Issakainen

2023

JIBE

View full text Add to dashboard Cite

show abstract

“…One of the most popular methods for processing time series is Recurrent Neural Networks (RNNs) [25]. This method is widely used for Time Series Classification (TSC), for example in forecasting [26,27], as RNNs are able to preserve information between neurons over the time line [28].…”

Section: Time-series Based Modelsmentioning

confidence: 99%

Using LSTM to Identify Help Needs in Primary School Scratch Students

Imbernón Cuadrado,

Manjarrés Riesco,

de la Paz López

2023

Applied Sciences

View full text Add to dashboard Cite

In the last few years, there has been increasing interest in the use of block-based programming languages as well as in the ethical aspects of Artificial Intelligence (AI) in primary school education. In this article, we present our research on the automatic identification of the need for assistance among primary school children performing Scratch exercises. For data collection, user experiences have been designed to take into account ethical aspects, including gender bias. Finally, a first-in-class distance calculation method for block-based programming languages has been used in a Long Short-Term Memory (LSTM) model, with the aim of identifying when a primary school student needs help while he/she carries out Scratch exercises. This model has been trained twice: the first time taking into account the gender of the students, and the second time excluding it. The accuracy of the model that includes gender is 99.2%, while that of the model that excludes gender is 91.1%. We conclude that taking into account gender in training this model can lead to overfitting, due to the under-representation of girls among the students participating in the experiences, making the model less able to identify when a student needs help. We also conclude that avoiding gender bias is a major challenge in research on educational systems for learning computational thinking skills, and that it necessarily involves effective and motivating gender-sensitive instructional design.

show abstract

“…When a piece of data is inputted, the sigmoid activation function will compare it to [0, 1]. Here, 0 means that no amount is allowed to pass through, and 1 represents that any amount can pass [34]. Suppose the output value is within the specified range.…”

Section: Input Layer Hidden Layermentioning

confidence: 99%

Optimizing Film Companies’ Marketing Strategy Using Blockchain and Recurrent Neural Network Model

Liu

2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

With the growing scale of the domestic film industry, the output of domestic films is also increasing. The design and execution problems in ticket marketing strategies adversely affect the revenue of domestic films. This paper aims to propose solutions to optimize film companies’ marketing strategies by analyzing the marketing environment and current situation to increase the income of domestic films. Firstly, the current situation of BJ’s marketing is analyzed, and the main problems are clarified. Secondly, the necessity and feasibility of applying blockchain technology to the operation and management of film companies are introduced. New marketing strategies and safeguards have been developed by analyzing the target market and optimizing the program. A quantitative method is used to predict a new movie’s box office in its premiere month. The proposed method introduces three factors affecting the box office: new film positioning, film marketing, and film prerating, as input variables. Besides, a Recurrent Neural Network (RNN) is implemented to predict the monthly box office of the premiere of new films. The results show that the predicted monthly box office of the movie adopting the optimized marketing strategy is 1,451,718.6 CNY, which is smaller than the target box office of 1414029.8. The Mean Absolute Error (MAE) is only 0.026. The proposed model’s Root Mean Square Error (RMSE) is 0.45 for the long-term prediction of a single movie price. The MAE is 0.106, and the accuracy is 0.80. The model proposed beats the unimproved Long Short-Term Memory (LSTM) model and the Autoregressive Moving Average (ARMA) model. This paper provides a reference for optimizing the film company’s marketing system.

show abstract

Financial Times Series Forecasting of Clustered Stocks

Cited by 7 publications

References 26 publications

Clustering-based value investing strategy in the Helsinki Stock Exchange: k-means algorithm

Clustering-based value investing strategy in the Helsinki Stock Exchange: k-means algorithm

Using LSTM to Identify Help Needs in Primary School Scratch Students

Optimizing Film Companies’ Marketing Strategy Using Blockchain and Recurrent Neural Network Model

Contact Info

Product

Resources

About