2 years, 6 months ago

FedCSIS 2022 Challenge: Predicting the Costs of Forwarding Contracts

FedCSIS 2022 Challenge: Predicting the Costs of Forwarding Contracts is the 8th data mining competition organized in association with Conference on Computer Science and Intelligence Systems (https://fedcsis.org/). At this year's competition, the task is to predict the costs related to the execution of forwarding contracts. The challenge is sponsored by Control System Software (https://controlsystem.com.pl/).

The topic of this year's data mining competition is the prediction of the costs related to the execution of forwarding contracts. The data sets made available to participants contain 6 years of history of orders appearing on the transport exchange, along with details such as the type of order, basic characteristics of the shipped goods (e.g., dimensions, special requirements), as well as the expected route that a driver will have to cover. The task for the competition participants is to develop a predictive model that assesses the actual costs of individual orders as accurately as possible. Such a model will be used in the future to support Freight Forwarders in selecting profitable contracts. The sponsor of the competition is Control System Software – a software company that has been delivering solutions for the Transportation, Spedition, and Logistics industry for 20 years.

Special session at FedCSIS 2022: 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, innovativeness of their approach, and quality of the submitted report.

Terms & Conditions
 
 
Rank Team Name Is Report   Preliminary Score Final Score Submissions
1
Dymitr
True True 0.1398 0.138300 619
2
Cyan
True True 0.1402 0.139100 181
3
hieuvq
True True 0.1396 0.140700 159
4
Lord of the Machine Learning
True True 0.1434 0.142000 147
5
baseline
True True 0.1491 0.147500 5
6
kubapok
True True 0.1502 0.149400 32
7
DeepIf
True True 0.1500 0.149800 28
8
Stan
True True 0.1529 0.151900 131
9
Artur Budzyński
True True 0.1549 0.152000 45
10
Nindza Zhelki
True True 0.1567 0.157300 36
11
flail1123
True True 0.1628 0.159600 24
12
MEM
True True 0.1615 0.161000 42
13
HBKU CS
True True 0.1653 0.162500 42
14
Paweł Putra
True True 0.1715 0.170100 31
15
Alex-POLSL
True True 0.1712 0.170400 20
16
Vexam
True True 0.1743 0.171400 22
17
kz
True True 0.1736 0.172700 10
18
fabiolapereira
True True 0.1783 0.174700 11
19
Maksymilian Grochowski
True True 0.1858 0.181700 12
20
Łukasz Orlikowski
True True 0.2103 0.210100 5
21
team
True True 0.2122 0.212800 7
22
SJIR
True True 0.2385 0.233600 7
23
SoloTeam
True True 0.4474 0.444100 1
24
Cake
True True 1.4975 1.494100 6
25
DenseDropout
False True 0.1505 No report file found or report rejected. 10
26
krzmip
False True 0.1509 No report file found or report rejected. 133
27
aaaaacacsacs
False True 0.1650 No report file found or report rejected. 11
28
Mario
False True 0.1660 No report file found or report rejected. 12
29
Adma
False True 0.1699 No report file found or report rejected. 2
30
hawkz
False True 0.1731 No report file found or report rejected. 27
31
Aidan
False True 0.1735 No report file found or report rejected. 5
32
rdeggau
False True 0.1757 No report file found or report rejected. 32
33
Siasio
False True 0.1758 No report file found or report rejected. 3
34
lov505
False True 0.1813 No report file found or report rejected. 6
35
Choraden
False True 0.1819 No report file found or report rejected. 13
36
michalm
False True 0.1824 No report file found or report rejected. 2
37
rllaskowski
False True 0.1836 No report file found or report rejected. 16
38
Bart
False True 0.1866 No report file found or report rejected. 3
39
DeepSpeditor
False True 0.1867 No report file found or report rejected. 6
40
KaLambda
False True 0.1894 No report file found or report rejected. 12
41
WhyNot
False True 0.1938 No report file found or report rejected. 2
42
Jakub Panasiuk
False True 0.2203 No report file found or report rejected. 30
43
Delavock
False True 0.2256 No report file found or report rejected. 13
44
csy
False True 0.2312 No report file found or report rejected. 10
45
Gr4g45
False True 0.2386 No report file found or report rejected. 9
46
rkli
False True 0.4200 No report file found or report rejected. 12
47
RamazanY
False True 0.5035 No report file found or report rejected. 1
48
yoggo
False True 0.5670 No report file found or report rejected. 10
49
Maciejs
False True 0.6990 No report file found or report rejected. 4
50
blablabla
False True 0.8367 No report file found or report rejected. 2
51
Zyndri123
False True 1.0738 No report file found or report rejected. 1

The FedCSIS 2022 Challenge: Predicting the Costs of Forwarding Contracts challenge has come to an end. 135 teams from 24 countries from all over the world competed to predict the costs related to the execution of forwarding contracts. 1945 correctly formatted solutions were sent. 

Congratulations to everyone who took up the challenge and submitted their solutions!

We are pleased to announce the winners of the competition:

  • 1s place: Dymitr team - Dymitr Ruta, David Ming Liu, Ling Cen from the United Arab Emirates
  • 2nd place: Cyan team - Haitao Xiao, Yuling Liu, Dan Du, Zhigang Lu from China
  • 3rd place: hieuvq team - Quang Hieu Vu from Vietnam

The results of their work will be presented during a special session at the 17th Conference on Computer Science and Intelligence Systems, FedCSIS 2022.

We are also happy to announce that the additional prize for the most practical solution has been awarded to Sławomir Piroński from the Lord of the Machine Learning team!

This year's edition of the competition was organized by FedCSIS in cooperation with PTI and QED Software. The sponsor of the competition was Control System Software.

The task in this challenge is to design an accurate method for predicting costs associated with forwarding contracts, based on contract data and planned routes. The available training data sets describe a five-year history of contracts accepted by a large Polish company. In particular, the training data consist of two tables: css_main_training.csv and css_routes_training.csv. The first one contains basic information about the contracts, and the second one describes the main sections of the planned routes associated with each contract. In both tables, the first column (i.e., id_contract) contains identifiers that allow matching records from css_main_training.csv and css_routes_training.csv files. Additionally, the second column in the css_main_training.csv file (i.e., expenses) contains information about the prediction target. Values in this column are available only for the training data. Short descriptions of data columns will be available in separate files in the Data files section.

Additionally, for the convenience of participants, we provide an additional data table containing historical wholesale fuel prices for the period of training and test data.

Solution format: the test data is also divided into two separate tables, i.e., css_main_test.csv and css_routes_test.csv. They have the same format as the corresponding training files but values from the column expenses are missing in css_main_test.csv.

Solutions in this competition should be submitted to the online evaluation system as text files with predictions for test instances. Each row of the solution file should contain exactly one prediction. The ordering of the predictions should be the same as the ordering of instances from the css_main_test.csv file. In total, the solution file should contain exactly 72452 predictions.

Evaluation: the quality of submissions will be evaluated using the RMSE measure.  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 which submit a report describing their approach before the end of the challenge will qualify for the final evaluation.

Please log in to the system!
  • May 27, 2022 (23:59 GMT): deadline for submitting the predictions
  • May 29, 2022 (23:59 GMT): deadline for sending the reports, end of the competition
  • June 03, 2022: online publication of the final results, sending invitations for submitting short papers for the special session at FedCSIS'22
  • July 01, 2022: deadline for submitting invited papers
  • July 08, 2022: notification of paper acceptance
  • July 21, 2022: 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 our sponsors:

  •     1,000 USD for the winning solution (+ the cost of one FedCSIS 2022 registration)
  •     500 USD for the 2nd place solution (+ the cost of one FedCSIS 2022 registration)
  •     250 USD for the 3rd place solution (+ the cost of one FedCSIS 2022 registration)

Moreover, Control System Software may award an additional prize (250 USD + the cost of one FedCSIS 2022 registration) to the team that develops the most practical solution to the task.

  •     Antoni Jamiołkowski, QED Software
  •     Andrzej Janusz, QED Software & University of Warsaw
  •     Rafał Tyl, QED Software
  •     Jacek Kamiński, QED Software
  •     Michał Okulewicz, Control System Software
  •     Juliusz Taniewski, Control System Software

In case of any questions please post on the competition forum or write an email at contact {at} knowledgepit.ml

This forum is for all users to discuss matters related to the competition. Good manners apply!
  Discussion Author Replies Last post
when is the deadline to merge teams? M 2 by M
Saturday, May 14, 2022, 18:23:46
Test cases with no predictions Artur 2 by Artur
Wednesday, April 27, 2022, 21:05:54
the backend evaluation program stopped since evening around 10:30pm 22 April 2022 M 4 by M
Saturday, April 23, 2022, 14:17:08
Schedule update Andrzej 0 by Andrzej
Thursday, April 07, 2022, 15:02:44
Error reading csv files Debojit 2 by Debojit
Wednesday, March 30, 2022, 10:05:19
Route end datetime is earlier than route start datetime Henry 2 by Henry
Friday, March 25, 2022, 14:09:35
Important announcement Andrzej 0 by Andrzej
Friday, March 18, 2022, 10:51:05
Welcome to the FedCSIS 2022 Challenge Andrzej 0 by Andrzej
Tuesday, March 08, 2022, 16:24:43