1 month, 1 week from now

FedCSIS 2024 Data Science Challenge: Predicting Stock Trends

FedCSIS 2024 Data Science Challenge: Predicting Stock Trends is the 10th data science challenge organized under the auspices of the Conference on Computer Science and Intelligence Systems (https://fedcsis.org/). In this anniversary edition, the task is related to financial data - participants are asked to predict the performance of investments in selected stocks from several industry sectors. The competition is sponsored by Mobi Banka (https://www.mobibanka.rs/en/consumer/) and the Conference on Computer Science and Intelligence Systems series.

The topic of this year's data science competition is the prediction of stock trends. The dataset contains key financial indicators for 300 companies chosen from 11 different sectors of the S&P 500 index, from 10 years. Each company is described by values of 58 indicators that are derived from its financial statements. The dataset also contains information on 1-year change for each indicator, which can indicate a trend in the considered values. The task for the competition participants is to develop a predictive model able to accurately forecast stock trend movements based on the provided financial fundamental data. Such a model could have a vital role in algorithmic or manual trading, providing the trading signals for making decisions about whether it is a good moment to buy or sell the stock, or maybe not to trade at all. The competition's sponsor is Mobi Banka (part of the PPF group) – the first bank in the Western Balkan region where banking is done fully mobile.

Special session at FedCSIS 2024: As in previous years, a special session devoted to the competition will be held at the conference. We will invite authors of selected challenge reports to extend them for publication in the conference proceedings (after reviews by Organizing Committee members) and presentation at the conference. The papers will be indexed by the IEEE Digital Library and Web of Science. The invited teams will be chosen based on their final rank, the innovativeness of their approach, and the quality of the submitted report.

Terms & Conditions
Please log in to the system!
Rank Team Name Score Submission Date
0.6683 2024-03-24 01:19:45
0.6782 2024-03-23 23:30:45
0.7178 2024-03-23 15:56:45
0.7376 2024-03-25 10:07:46
0.7475 2024-03-14 04:03:16
0.7525 2024-03-13 22:56:50
0.7574 2024-03-28 20:25:49
0.7723 2024-03-15 01:25:37
0.7772 2024-03-31 22:47:31
0.7871 2024-03-22 17:22:54
0.7871 2024-04-14 13:29:20
0.8069 2024-03-28 00:19:44
0.8168 2024-04-11 14:44:38
0.8218 2024-04-2 10:13:36
0.8218 2024-04-11 13:57:38
0.8267 2024-04-3 20:03:13
0.8366 2024-04-3 13:03:00
0.8515 2024-03-2 14:04:01
0.8515 2024-03-24 16:55:42
0.8564 2024-03-23 21:46:55
418 teapots
0.8564 2024-03-28 13:53:50
Stokastik Heinz
0.8564 2024-04-14 20:08:53
0.9010 2024-04-10 16:18:13
0.9059 2024-04-15 18:50:58
0.9752 2024-04-12 22:38:50

The task in this challenge is to design an accurate method for predicting a trading action (buy, sell, hold). The available training data contains 8,000 instances with fundamental financial data in a tabular format (CSV file with semicolons used as separators). Each instance in data represents an event – a financial statement announcement for one of the chosen 300 companies. It contains information on the company’s sector, values for 58 key financial indicators, 1-year (absolute) change for each of the 58 indicators, target class information (the column 'Class'), and risk-return performance for a period after the announcement (the column 'Perform').

Please note that the data contains two distinct types of missing values that have different semantics. One corresponds to non-available/missing information and another one can be interpreted as non-applicable. In data, one type is marked by "NA" string and another is just an empty string (there is no value).

Solution format: the test data, containing 2,000 instances, is also provided as a CSV file. The test file has the same format and naming scheme as the training data but it does not contain columns 'Class' and 'Perform'.

Solutions in this competition should be submitted to the online evaluation system as a text file with exactly 2,000 lines containing predictions for test instances. Each line in the submission should contain a single number from the set {1, 0, -1} that indicates the predicted trading action for the event. The ordering of predictions should be the same as the ordering of the test set.

Evaluation: the quality of submissions will be evaluated using the average error cost measure with the error cost matrix given below:

  -1 0 1
-1 0 1 2
0 1 0 1
1 2 1 0


In particular, the error value is computed as: err = (confusion_matrix(preds, gt) * cost_matrix)/length(gt)), where the multiplication is done element-wise.

Solutions will be evaluated online, and the preliminary results will be published on the public leaderboard. The preliminary score will be computed on a small subset of the test records, fixed for all participants. The final evaluation will be performed after the completion of the competition using the remaining part of the test records. Those results will also be published online. It is important to note that only teams that submit a report describing their approach before the end of the challenge will qualify for the final evaluation.

In order to download competition files you need to be enrolled.
  • March 1, 2024: start of the competition
  • May 10 May 24, 2024 (23:59 GMT): deadline for submitting the predictions
  • May 12 May 26, 2024 (23:59 GMT): deadline for sending the reports, end of the competition
  • May 19 June 2, 2024: online publication of the final results, sending invitations for submitting short papers for the special session at FedCSIS'24
  • June 16, 2024: deadline for submitting invited papers
  • June 30, 2024: notification of paper acceptance
  • July 9, 2024: camera-ready of accepted papers, and registration for the conference are due

Authors of the top-ranked solutions (based on the final evaluation scores) will be awarded prizes funded by the Sponsors:

  •     1000 EUR for the winning solution + one free FedCSIS 2024 registration
  •     500 EUR for the 2nd place solution + one free FedCSIS 2024 registration
  •     300 EUR for the 3rd place solution + one free FedCSIS 2024 registration
  •     special award of 300 EUR for the solution with the highest cummulative performance + one free FedCSIS 2024 registration
  • Aleksandar M. Rakićević, University of Belgrade
  • Pavle D. Milošević, University of Belgrade
  • Ivana T. Dragović, University of Belgrade
  • Ana M. Poledica, University of Belgrade
  • Milica M. Zukanović, University of Belgrade
  • Ivan S. Luković, University of Belgrade
  • Andrzej Janusz, Queensland University of Technology / QED Software
  • Dominik Ślęzak, University of Warsaw / QED Software

The main sponsor of the competition, Mobi Banka, is a part of the PPF group and the first bank in the Western Balkan region where banking is done differently - fully mobile. With its unique user platform for mobile phones and PCs, it offers innovative digital banking services, simple to use and available anytime and anywhere.

This forum is for all users to discuss matters related to the competition. Good manners apply!
  Discussion Author Replies Last post
Deadline extension - May 24, 2024 Aleksandar 0 by Aleksandar
Wednesday, April 10, 2024, 11:05:50
Unable to merge teams 1 by Andrzej
Tuesday, April 02, 2024, 17:53:36
metric code Karol 2 by Dymitr
Wednesday, March 13, 2024, 20:25:33
Time order Dymitr 1 by Aleksandar
Friday, March 08, 2024, 16:30:31