Deep Bi-Directional LSTM Networks for Device Workload Forecasting

Ruta, Dymitr; Cen, Ling; Vu, Quang Hieu

doi:10.15439/2020f213

Cited by 12 publications

(6 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Besides the above-discussed baseline, Table I reports the final ranks, scores, and the number of submissions for some of the best performing teams. More details about some of those teams can be found in [3], [6], [9], [10]. The best submitted solution, i.e.…”

Section: Competition Resultsmentioning

confidence: 99%

Network Device Workload Prediction: A Data Mining Challenge at Knowledge Pit

Janusz

Przyborowski

Biczyk³

et al. 2020

Proceedings of the 2020 Federated Conference on Computer Science and Information Systems

View full text Add to dashboard Cite

We describe the 7th edition of the international data mining competition held at Knowledge Pit in association with the FedCSIS conference series. The goal was to predict workloadrelated characteristics of monitored network devices. We analyze solutions uploaded by the most successful participants. We investigate prediction errors which had the greatest influence on their results. We also present our own baseline solution which turned out to be the most reliable in the final evaluation.

show abstract

Section: Competition Resultsmentioning

confidence: 99%

Network Device Workload Prediction: A Data Mining Challenge at Knowledge Pit

Janusz

Przyborowski

Biczyk³

et al. 2020

Proceedings of the 2020 Federated Conference on Computer Science and Information Systems

View full text Add to dashboard Cite

show abstract

“…As you can expect, the combination of the two models using the same set of features does not help to make much improvement in the model accuracy. Instead, we employ this strategy simply to get a stable prediction result as our main concern is always the overfitting issue given the small amount of data used for the public leaderboard, which we experienced in the past two competitions of 2020 [2], [3] and was presented in the paper [4].…”

Section: Model Design and Implementationmentioning

confidence: 99%

Key Factors to Consider when Predicting the Costs of Forwarding Contracts

Vu¹,

Cen²,

Ruta³

et al. 2022

Annals of Computer Science and Information Systems

Self Cite

View full text Add to dashboard Cite

Predicting the cost of forwarding contracts is a typical problem that logistics companies need to solve in order to optimize their business for a better profit. This is the challenge defined in the FedCSIS 2022 Competition where a fiveyear history of contract data and their delivery routes from a large Polish logistics company are provided to train a Machine Learning model. In addition to the contract data, historical wholesale fuel prices and euro exchange rates at the contract time are also provided. To address this challenge, we first designed a basic solution where we focused on feature engineering to find good impact features for the model. After that, the same set of features were used to train two different models: one using XGBoost and the other using LightGBM. The average predictions of the two boosting models were then used as the predictions for the next post-processing step. Finally, in the post-processing step, we designed and trained a simple linear regression model to capture the average monthly changes of the contract cost, given the changes of the fuel prices and euro exchange rates. These captured changes were used to post-process (adjust) the predictions in the previous step to address the issue that treebased models could not predict the value that they did not see before. While the basic solution with careful feature selection gave us a place in the top-5, our post-processing strategy in the last step helped us win the 3 rd prize in the competition.

show abstract

“…In the paper [10] a case study for using long shortterm memory (LSTM) recurrent neural networks (RNN) was proposed. Deep Bi-Directional LSTM Networks was presented in [11]. The authors of the paper [12] proposed a novel forecasting method that combined the deep learning method -LSTM -and random forest (RF) for demand forecasting problems.…”

Section: Related Workmentioning

confidence: 99%

Impact of time series clustering on fuel sales prediction results

Henzel¹,

Bularz²,

Sikora³

2021

Position and Communication Papers of the 16th Conference on Computer Science and Intelligence Systems

View full text Add to dashboard Cite

The purpose of the paper is to check the impact of data clustering in the process of predicting demand. We checked different ways of adding information about similar datasets to the forecasting process and we grouped the measurements in multiple ways. The experiments were executed on 50 time series describing fuels sales (gasoline and diesel sales) on 25 petrol stations from an international company. We described the data preparation process and feature extraction process. In the 9 presented experiments, we used the XGBoost algorithm and some typical time series forecasting methods (ARIMA, moving average). We showed a case study for two datasets and we discussed the practical usage of the tested solutions. The results showed that the solution which used XGBoost model utilising data gathered from all available petrol stations, in general, worked the best and it outperformed more advanced approaches as well as typical time series methods.

show abstract

Deep Bi-Directional LSTM Networks for Device Workload Forecasting

Cited by 12 publications

References 12 publications

Network Device Workload Prediction: A Data Mining Challenge at Knowledge Pit

Network Device Workload Prediction: A Data Mining Challenge at Knowledge Pit

Key Factors to Consider when Predicting the Costs of Forwarding Contracts

Impact of time series clustering on fuel sales prediction results

Contact Info

Product

Resources

About