Optimized Early Prediction of Business Processes with Hyperdimensional Computing
Abstract
:1. Introduction
- We propose a novel method for process outcome prediction based on Hyperdimensional Computing. Unlike conventional approaches, our method utilizes fixed-length vectors to maintain event patterns and attributes, effectively preserving memory. Also, unlike previous methods that require iterative encoding and training for prediction at different indices, in our proposed method, we adopt a novel approach wherein, for the observation of a new event or attribute, we add its corresponding hypervector to the previously constructed hypervector. This eliminates the need to encode and train an ongoing process from scratch.
- Through eliminating traditional hyper-parameter tuning and incorporating a wise storage mechanism for subsets of trace prefixes, our proposed method enables the construction of a classifier on historical data using basic element-wise operations along vectors.
- Choosing event attributes that determine the class of a process requires domain knowledge, but such information is lacking in many datasets. Therefore, we designed two algorithm versions: one, HDC-based, considers only patterns and event order within processes, and the other, attribute-based HDC (Att-HDC), considers patterns within sequence of events, event order, and event attributes.
- The experimental results demonstrate the F1-score improving by up to 14% compared to the best baseline (XGBoost [19]) and AUC scores improving by an average of 6% in the key early process stages. This highlights the algorithm’s ability to provide more accurate predictions early on, without sacrificing runtime efficiency. Furthermore, we showcase our proposed method’s high performance when training on a randomly chosen subset of the input data, eliminating the need for compute-intensive sampling methods. Our proposed method yields a similar F1-score and AUC score with only a sampling ratio of 0.5 of the training data. Thus, we propose more accurate early prediction, eliminating the need for passing over the whole training data.
2. Background
2.1. Outcome-Oriented Predictive Process Monitoring
2.2. Hyperdimensional Computing
3. Related Work
4. HDC-Based Framework for Predicting Process Outcomes
4.1. Encoding
Algorithm 1: HDC Encoding Algorithm |
Algorithm 2: Function: LeftRotate |
Input: Vector , Number of positions Output: Vector rotated left by indices 1 return rotated left by indices |
Algorithm 3: Function: RandomBinaryVector |
Input: Dimension D Output: A D-dimensional vector with random binary (0 or 1) elements 1 return A D-dimensional vector with random binary elements |
4.2. Single-Pass Encoding and Inference
4.3. Training
Algorithm 4: HDC Training |
4.4. Inference (Prediction)
Algorithm 5: HDC Inference |
4.5. Retraining
4.6. Attribute Binding in Att-HD
Algorithm 6: Att-HDC attribute binding |
4.7. Proposed HDC-Based Framework
5. Experimental Evaluations
5.1. Datasets and Labeling Functions
- (1)
- The event log represents the history of loan application processes in a Dutch financial institute. Based on the literature, we define three labels for this dataset: , , and , corresponding to cases terminated as approved, cancelled, or declined.
- (2)
- consists of five datasets provided by Dutch municipalities, containing event logs of building permit application processes. For labeling processes, the following Linear-time Temporal Logic (LTL) rule based on the literature is applied in each dataset i, where denotes the number of the municipality: “ G (send confirmation receipt) → F(retrieve missing data)”, where is the LTL rule, and the label is 0 if is violated in the trace, and 1 otherwise. Operator G means that the activity should always hold in the subsequent positions of a path, and F means it should finally hold somewhere in the subsequent positions of a path. G → F is the conditional propositions (). It expresses that if the confirmation receipt is always being sent, the missing data should be eventually retrieved.
- (3)
- The event log is an extended version of with richer and cleaner data. Similar to , we define three labels referred to as , , and for processes terminating in approved, canceled, and declined events, respectively.
- (4)
- is collected from a large multinational company in the Netherlands and contains the handling of a purchase order. We label traces in this event log based on whether they terminate in the “Clear Invoice” event or not.
5.2. Evaluation Metrics
5.3. Results
5.4. Instance Sampling
6. Discussion of Limitations and Future Work
7. Conclusions
Author Contributions
Funding
Data Availability Statement
Conflicts of Interest
References
- Teinemaa, I.; Dumas, M.; Rosa, M.L.; Maggi, F.M. Outcome-oriented predictive process monitoring: Review and benchmark. ACM Trans. Knowl. Discov. Data (TKDD) 2019, 13, 1–57. [Google Scholar] [CrossRef]
- van der Aalst, W.; Reijers, H.; Weijters, A.; van Dongen, B.; Alves de Medeiros, A.; Song, M.; Verbeek, H. Business process mining: An industrial application. Inf. Syst. 2007, 32, 713–732. [Google Scholar] [CrossRef]
- Márquez-Chamorro, A.E.; Resinas, M.; Ruiz-Cortés, A. Predictive monitoring of business processes: A survey. IEEE Trans. Serv. Comput. 2017, 11, 962–977. [Google Scholar] [CrossRef]
- Di Francescomarino, C.; Dumas, M.; Maggi, F.M.; Teinemaa, I. Clustering-based predictive process monitoring. IEEE Trans. Serv. Comput. 2016, 12, 896–909. [Google Scholar] [CrossRef]
- Evermann, J.; Rehse, J.R.; Fettke, P. A deep learning approach for predicting process behaviour at runtime. In Proceedings of the International Conference on Business Process Management, Rio de Janeiro, Brazil, 18–22 September 2016; Springer: Berlin/Heidelberg, Germany, 2016; pp. 327–338. [Google Scholar]
- Morariu, C.; Morariu, O.; Răileanu, S.; Borangiu, T. Machine learning for predictive scheduling and resource allocation in large scale manufacturing systems. Comput. Ind. 2020, 120, 103244. [Google Scholar] [CrossRef]
- Aalikhani, R.; Fathian, M.; Rasouli, M.R. Comparative Analysis of Classification-Based and Regression-Based Predictive Process Monitoring Models for Accurate and Time-Efficient Remaining Time Prediction. IEEE Access 2024, 12, 67063–67093. [Google Scholar] [CrossRef]
- Verenich, I.; Dumas, M.; Rosa, M.L.; Maggi, F.M.; Teinemaa, I. Survey and Cross-Benchmark Comparison of Remaining Time Prediction Methods in Business Process Monitoring. ACM Trans. Intell. Syst. Technol. 2019, 10, 1–34. [Google Scholar] [CrossRef]
- Maggi, F.M.; Di Francescomarino, C.; Dumas, M.; Ghidini, C. Predictive monitoring of business processes. In Proceedings of the International Conference on Advanced Information Systems Engineering, Thessaloniki, Greece, 16–20 June 2014; Springer: Berlin/Heidelberg, Germany, 2014; pp. 457–472. [Google Scholar]
- Wang, J.; Yu, D.; Liu, C.; Sun, X. Outcome-oriented predictive process monitoring with attention-based bidirectional LSTM neural networks. In Proceedings of the 2019 IEEE International Conference on Web Services (ICWS), Milan, Italy, 8–13 July 2019; IEEE: Piscataway, NJ, USA, 2019; pp. 360–367. [Google Scholar]
- Xing, Z.; Pei, J.; Keogh, E. A brief survey on sequence classification. ACM Sigkdd Explor. Newsl. 2010, 12, 40–48. [Google Scholar] [CrossRef]
- Fani Sani, M.; Vazifehdoostirani, M.; Park, G.; Pegoraro, M.; van Zelst, S.J.; van der Aalst, W.M. Performance-preserving event log sampling for predictive monitoring. J. Intell. Inf. Syst. 2023, 61, 53–82. [Google Scholar] [CrossRef]
- Weytjens, H.; De Weerdt, J. Learning uncertainty with artificial neural networks for predictive process monitoring. Appl. Soft Comput. 2022, 125, 109134. [Google Scholar] [CrossRef]
- Park, G.; Song, M. Optimizing Resource Allocation Based on Predictive Process Monitoring. IEEE Access 2023, 11, 38309–38323. [Google Scholar] [CrossRef]
- Leontjeva, A.; Conforti, R.; Di Francescomarino, C.; Dumas, M.; Maggi, F.M. Complex symbolic sequence encodings for predictive monitoring of business processes. In Proceedings of the Business Process Management: 13th International Conference, BPM 2015, Innsbruck, Austria, 31 August–3 September 2015; Proceedings 13. Springer: Berlin/Heidelberg, Germany, 2015; pp. 297–313. [Google Scholar]
- Ramirez-Alcocer, U.M.; Tello-Leal, E.; Romero, G.; Macías-Hernández, B.A. A Deep Learning Approach for Predictive Healthcare Process Monitoring. Information 2023, 14, 508. [Google Scholar] [CrossRef]
- De Leoni, M.; Van der Aalst, W.M.; Dees, M. A general framework for correlating business process characteristics. In Proceedings of the International Conference on Business Process Management, Haifa, Israel, 7–11 September 2014; Springer: Berlin/Heidelberg, Germany, 2014; pp. 250–266. [Google Scholar]
- Vazifehdoostirani, M.; Abbaspour Onari, M.; Grau, I.; Genga, L.; Dijkman, R. Uncovering the Hidden Significance of Activities Location in Predictive Process Monitoring. In Proceedings of the International Conference on Process Mining, Rome, Italy, 23–27 October 2023; Springer: Berlin/Heidelberg, Germany, 2023; pp. 191–203. [Google Scholar]
- El-Khawaga, G.; Abu-Elkheir, M.; Reichert, M. Xai in the context of predictive process monitoring: An empirical analysis framework. Algorithms 2022, 15, 199. [Google Scholar] [CrossRef]
- Camargo, M.; Dumas, M.; González-Rojas, O. Learning accurate LSTM models of business processes. In Proceedings of the International Conference on Business Process Management, Vienna, Austria, 1–6 September 2019; Springer: Berlin/Heidelberg, Germany, 2019; pp. 286–302. [Google Scholar]
- De Smedt, J.; De Weerdt, J. Predictive process model monitoring using long short-term memory networks. Eng. Appl. Artif. Intell. 2024, 133, 108295. [Google Scholar] [CrossRef]
- Kim, S.; Comuzzi, M.; Di Francescomarino, C. Understanding the Impact of Design Choices on the Performance of Predictive Process Monitoring. In Proceedings of the International Conference on Process Mining, Rome, Italy, 23–27 October 2023; Springer: Berlin/Heidelberg, Germany, 2023; pp. 153–164. [Google Scholar]
- Kanerva, P. Hyperdimensional computing: An introduction to computing in distributed representation with high-dimensional random vectors. Cogn. Comput. 2009, 1, 139–159. [Google Scholar] [CrossRef]
- Thomas, A.; Dasgupta, S.; Rosing, T. Theoretical Foundations of Hyperdimensional Computing. J. Artif. Intell. Res. 2021, 72, 215–249. [Google Scholar] [CrossRef]
- Van Der Aalst, W. Process mining. Commun. ACM 2012, 55, 76–83. [Google Scholar] [CrossRef]
- Vidgof, M.; Wurm, B.; Mendling, J. The Impact of Process Complexity on Process Performance: A Study using Event Log Data. In Proceedings of the International Conference on Business Process Management, Utrecht, The Netherlands, 11–15 September 2023; Springer: Berlin/Heidelberg, Germany, 2023; pp. 413–429. [Google Scholar]
- Thapa, R.; Lamichhane, B.; Ma, D.; Jiao, X. Spamhd: Memory-efficient text spam detection using brain-inspired hyperdimensional computing. In Proceedings of the 2021 IEEE Computer Society Annual Symposium on VLSI (ISVLSI), Tampa, FL, USA, 7–9 July 2021; IEEE: Piscataway, NJ, USA, 2021; pp. 84–89. [Google Scholar]
- Imani, M.; Nassar, T.; Rahimi, A.; Rosing, T. Hdna: Energy-efficient dna sequencing using hyperdimensional computing. In Proceedings of the 2018 IEEE EMBS International Conference on Biomedical & Health Informatics (BHI), Las Vegas, NV, USA, 4–7 March 2018; IEEE: Piscataway, NJ, USA, 2018; pp. 271–274. [Google Scholar]
- Watkinson, N.; Givargis, T.; Joe, V.; Nicolau, A.; Veidenbaum, A. Class-modeling of septic shock with hyperdimensional computing. In Proceedings of the 2021 43rd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC), Virtual, 1–5 November 2021; IEEE: Piscataway, NJ, USA, 2021; pp. 1653–1659. [Google Scholar]
- Ge, L.; Parhi, K.K. Classification using hyperdimensional computing: A review. IEEE Circuits Syst. Mag. 2020, 20, 30–47. [Google Scholar] [CrossRef]
- Rahimi, A.; Benatti, S.; Kanerva, P.; Benini, L.; Rabaey, J.M. Hyperdimensional biosignal processing: A case study for EMG-based hand gesture recognition. In Proceedings of the 2016 IEEE International Conference on Rebooting Computing (ICRC), San Diego, CA, USA, 17–19 October 2016; IEEE: Piscataway, NJ, USA, 2016; pp. 1–8. [Google Scholar]
- Khaleghi, B.; Xu, H.; Morris, J.; Rosing, T.Š. tiny-hd: Ultra-efficient hyperdimensional computing engine for iot applications. In Proceedings of the 2021 Design, Automation & Test in Europe Conference & Exhibition (DATE), Grenoble, France, 1–5 February 2021; IEEE: Piscataway, NJ, USA, 2021; pp. 408–413. [Google Scholar]
- Akiba, T.; Sano, S.; Yanase, T.; Ohta, T.; Koyama, M. Optuna: A next-generation hyperparameter optimization framework. In Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, Anchorage, AK, USA, 4–8 August 2019; pp. 2623–2631. [Google Scholar]
- Asgarinejad, F.; Morris, J.; Rosing, T.; Aksanli, B. PIONEER: Highly Efficient and Accurate Hyperdimensional Computing using Learned Projection. In Proceedings of the 2024 29th Asia and South Pacific Design Automation Conference (ASP-DAC), Incheon, Republic of Korea, 22–25 January 2024; IEEE: Piscataway, NJ, USA, 2024; pp. 896–901. [Google Scholar]
- Pale, U.; Teijeiro, T.; Rheims, S.; Ryvlin, P.; Atienza, D. Combining general and personal models for epilepsy detection with hyperdimensional computing. Artif. Intell. Med. 2024, 148, 102754. [Google Scholar] [CrossRef]
- Nunes, I.; Heddes, M.; Givargis, T.; Nicolau, A.; Veidenbaum, A. GraphHD: Efficient graph classification using hyperdimensional computing. In Proceedings of the 2022 Design, Automation & Test in Europe Conference & Exhibition (DATE), Antwerp, Belgium, 14–23 March 2022; IEEE: Piscataway, NJ, USA, 2022; pp. 1485–1490. [Google Scholar]
- Hernández-Cano, A.; Zhuo, C.; Yin, X.; Imani, M. Reghd: Robust and efficient regression in hyper-dimensional learning system. In Proceedings of the 2021 58th ACM/IEEE Design Automation Conference (DAC), San Francisco, CA, USA, 5–9 December 2021; IEEE: Piscataway, NJ, USA, 2021; pp. 7–12. [Google Scholar]
- Ge, L.; Parhi, K.K. Robust clustering using hyperdimensional computing. IEEE Open J. Circuits Syst. 2024, 5, 102–116. [Google Scholar] [CrossRef]
- Kratsch, W.; Manderscheid, J.; Röglinger, M.; Seyfried, J. Machine learning in business process monitoring: A comparison of deep learning and classical approaches used for outcome prediction. Bus. Inf. Syst. Eng. 2021, 63, 261–276. [Google Scholar] [CrossRef]
- Di Francescomarino, C.; Ghidini, C.; Maggi, F.M.; Milani, F. Predictive process monitoring methods: Which one suits me best? In Proceedings of the International Conference on Business Process Management, Sydney, Australia, 9–14 September 2018; Springer: Berlin/Heidelberg, Germany, 2018; pp. 462–479. [Google Scholar]
- Rahimi, A.; Kanerva, P.; Rabaey, J.M. A robust and energy-efficient classifier using brain-inspired hyperdimensional computing. In Proceedings of the 2016 International Symposium on Low Power Electronics and Design, San Francisco, CA, USA, 8–10 August 2016; pp. 64–69. [Google Scholar]
- Ma, D.; Hao, C.; Jiao, X. Hyperdimensional computing vs. neural networks: Comparing architecture and learning process. In Proceedings of the 2024 25th International Symposium on Quality Electronic Design (ISQED), San Francisco, CA, USA, 3–5 April 2024; IEEE: Piscataway, NJ, USA, 2024; pp. 1–5. [Google Scholar]
- Kononenko, I.; Kukar, M. Machine Learning and Data Mining; Horwood Publishing: Chichester, UK, 2007. [Google Scholar]
- Bradley, A.P. The use of the area under the ROC curve in the evaluation of machine learning algorithms. Pattern Recognit. 1997, 30, 1145–1159. [Google Scholar] [CrossRef]
- Drodt, C.; Weinzierl, S.; Matzner, M.; Delfmann, P. Predictive Recommining: Learning Relations between Event Log Characteristics and Machine Learning Approaches for Supporting Predictive Process Monitoring. In Proceedings of the International Conference on Advanced Information Systems Engineering, Zaragoza, Spain, 12–16 June 2023; Springer: Berlin/Heidelberg, Germany, 2023; pp. 69–76. [Google Scholar]
- Alonso, P.; Shridhar, K.; Kleyko, D.; Osipov, E.; Liwicki, M. HyperEmbed: Tradeoffs between resources and performance in NLP tasks with hyperdimensional computing enabled embedding of n-gram statistics. In Proceedings of the 2021 International Joint Conference on Neural Networks (IJCNN), Shenzhen, China, 18–22 July 2021; IEEE: Piscataway, NJ, USA, 2021; pp. 1–9. [Google Scholar]
- Kanerva, P. Hyperdimensional computing: An algebra for computing with vectors. Advances in Semiconductor Technologies: Selected Topics Beyond Conventional CMOS; John Wiley & Sons: Hoboken, NJ, USA, 2022; pp. 25–42. [Google Scholar]
- Najafabadi, F.R.; Rahimi, A.; Kanerva, P.; Rabaey, J.M. Hyperdimensional computing for text classification. In Proceedings of the Design, Automation Test in Europe Conference Exhibition (DATE), Dresden, Germany, 14–18 March 2016; p. 1. [Google Scholar]
- Rosato, A.; Panella, M.; Kleyko, D. Hyperdimensional computing for efficient distributed classification with randomized neural networks. In Proceedings of the 2021 International Joint Conference on Neural Networks (IJCNN), Shenzhen, China, 18–22 July 2021; IEEE: Piscataway, NJ, USA, 2021; pp. 1–10. [Google Scholar]
Trace ID | Event Name | Timestamp | Resource and User | Cumulative Net Worth (EUR) |
---|---|---|---|---|
trace 338 | Create Purchase Order Item | 2018-01-02T03:20:00.000Z | batch-04 | 1833.0 |
Record Goods Receipt | 2018-01-22T16:33:00.000Z | user-031 | 1833.0 | |
Vendor creates invoice | 2018-01-25T22:59:00.000Z | NONE | 1833.0 | |
Record Invoice Receipt | 2018-02-02T12:28:00.000Z | user-007 | 1833.0 | |
Clear Invoice | 2018-02-22T15:17:00.000Z | user-002 | 1833.0 | |
trace 529 | Create Purchase Order Item | 2018-01-02T08:51:00.000Z | user-052 | 0.0 |
Record Goods Receipt | 2018-01-18T10:02:00.000Z | user-053 | 0.0 | |
trace 198181 | Create Purchase Order Item | 2018-10-15T05:34:00.000Z | user-119 | 15.0 |
Record Goods Receipt | 2018-10-18T11:43:00.000Z | user-080 | 15.0 | |
Create Purchase Order Item | 2018-10-24T21:59:00.000Z | NONE | 15.0 | |
Clear Invoice | 2018-11-15T14:35:00.000Z | user-002 | 15.0 |
Application Domain | Task & Reference | Dataset Type/Name | Performance |
---|---|---|---|
Image Classification | Classification [34] | Images (CIFAR10, MNIST, etc.) | Increased accuracy/energy efficiency vs. SOTA |
Genomics | Classification [28] | DNA sequences | Increased accuracy/lower time and energy vs. SOTA |
Graph Analytics | Classification [36] | Graphs | Faster inference vs. SOTA |
Economics and Energy | Regression [37] | Boston housing, CCPP, etc. | Faster and energy efficient vs. SOTA |
Bioinformatics | Clustering [38] | IRIS, ISOLET, RNA-seq, etc. | Higher clustering accuracy/less execution time vs. SOTA |
Symbol | Definition | Symbol | Definition |
---|---|---|---|
dimension of encoded data | hypervector of encoded data | ||
level hypervector | permutation by n indexes | ||
e | event | C | class hypervector |
t | trace | tri-gram of events | |
trace prefix | event attribute | ||
m | trace length | Q | # of quantized levels |
prediction event | l | quantizer’s level hypervector |
Dataset | Traces | Min Len | Median Len | Max Len | Unique Events | Event Attr. | Pos. Class Ratio |
---|---|---|---|---|---|---|---|
13,087 | 3 | 11 | 175 | 24 | 3 | 0.19 | |
13,087 | 3 | 11 | 175 | 24 | 3 | 0.22 | |
13,087 | 3 | 11 | 175 | 24 | 3 | 0.58 | |
1199 | 2 | 44 | 101 | 289 | 0 | 0.24 | |
832 | 1 | 54 | 132 | 304 | 0 | 0.19 | |
1409 | 3 | 42 | 124 | 277 | 0 | 0.20 | |
1053 | 1 | 44 | 116 | 272 | 0 | 0.16 | |
1156 | 5 | 50 | 154 | 285 | 0 | 0.31 | |
31,413 | 10 | 35 | 180 | 26 | 4 | 0.41 | |
31,413 | 10 | 35 | 180 | 26 | 4 | 0.12 | |
31,413 | 10 | 35 | 180 | 26 | 4 | 0.47 | |
251,734 | 1 | 5 | 990 | 42 | 3 | 0.72 |
Baseline Methods | Proposed Methods | Best HDC-Based vs. Best Baseline (%) | ||||||
---|---|---|---|---|---|---|---|---|
Dataset | XGBoost [19] | RF [1] | SVM [39] | LR [1] | Att-bi-LSTM [10] | HDC | Att-HDC | |
0.56 ± 0.06 | 0.56 ± 0.06 | 0.56 ± 0.06 | 0.56 ± 0.05 | 0.52 ± 0.02 | 0.66 ± 0.01 | 0.66 ± 0.01 | +10% | |
0.57 ± 0.08 | 0.57 ± 0.08 | 0.57 ± 0.08 | 0.57 ± 0.08 | 0.58 ± 0.09 | 0.66 ± 0.01 | 0.66 ± 0.01 | +8% | |
0.81 ± 0.15 | 0.81 ± 0.15 | 0.81 ± 0.16 | 0.81 ± 0.15 | 0.74 ± 0.17 | 0.73 ± 0.14 | 0.70 ± 0.13 | −8% | |
0.80 ± 0.17 | 0.82 ± 0.16 | 0.81 ± 0.16 | 0.82 ± 0.16 | 0.77 ± 0.14 | 0.85 ± 0.14 | 0.85 ± 0.14 | +3% | |
0.81 ± 0.17 | 0.81 ± 0.16 | 0.81 ± 0.11 | 0.82 ± 0.14 | 0.73 ± 0.20 | 0.82 ± 0.11 | 0.82 ± 0.11 | 0% | |
0.80 ± 0.17 | 0.81 ± 0.16 | 0.81 ± 0.12 | 0.83 ± 0.15 | 0.71 ± 0.18 | 0.86 ± 0.14 | 0.86 ± 0.14 | +3% | |
0.60 ± 0.38 | 0.57 ± 0.41 | 0.44 ± 0.38 | 0.46 ± 0.37 | 0.59 ± 0.34 | 0.85 ± 0.23 | 0.85 ± 0.23 | +23% | |
0.83 ± 0.14 | 0.81 ± 0.16 | 0.86 ± 0.11 | 0.83 ± 0.14 | 0.78 ± 0.15 | 0.82 ± 0.15 | 0.82 ± 0.15 | −1% | |
0.65 ± 0.12 | 0.52 ± 0.05 | 0.66 ± 0.13 | 0.65 ± 0.12 | 0.84 ± 0.15 | 0.59 ± 0.08 | 0.60 ± 0.11 | −24% | |
0.68 ± 0.15 | 0.69 ± 0.15 | 0.68 ± 0.15 | 0.66 ± 0.14 | 0.69 ± 0.15 | 0.67 ± 0.13 | 0.71 ± 0.14 | +2% | |
0.70 ± 0.15 | 0.70 ± 0.14 | 0.69 ± 0.15 | 0.68 ± 0.15 | 0.67 ± 0.14 | 0.74 ± 0.11 | 0.75 ± 0.13 | + 5% | |
0.70 ± 0.18 | 0.70 ± 0.09 | 0.70 ± 0.14 | 0.70 ± 0.24 | 0.69 ± 0.15 | 0.75 ± 0.09 | 0.76 ± 0.09 |
Baseline Methods | Proposed Methods | Best HDC-Based vs. Best Baseline (%) | ||||||
---|---|---|---|---|---|---|---|---|
Dataset | XGBoost [19] | RF [1] | SVM [39] | LR [1] | Att-bi-LSTM [10] | HDC | Att-HDC | |
0.53 ± 0.10 | 0.55 ± 0.09 | 0.53 ± 0.10 | 0.53 ± 0.14 | 0.53 ± 0.09 | 0.55 ± 0.19 | 0.60 ± 0.12 | +7% | |
0.54 ± 0.12 | 0.54 ± 0.12 | 0.54 ± 0.11 | 0.55 ± 0.12 | 0.53 ± 0.12 | 0.59 ± 0.11 | 0.59 ± 0.11 | +4% | |
0.82 ± 0.15 | 0.78 ± 0.21 | 0.78 ± 0.21 | 0.78 ± 0.20 | 0.77 ± 0.19 | 0.67 ± 0.23 | 0.69 ± 0.23 | −14% | |
0.73 ± 0.23 | 0.74 ± 0.23 | 0.68 ± 0.22 | 0.70 ± 0.27 | 0.66 ± 0.13 | 0.76 ± 0.17 | 0.76 ± 0.17 | +2% | |
0.74 ± 0.21 | 0.76 ± 0.23 | 0.73 ± 0.18 | 0.77 ± 0.22 | 0.69 ± 0.11 | 0.73 ± 0.16 | 0.73 ± 0.16 | −3% | |
0.76 ± 0.22 | 0.76 ± 0.22 | 0.73 ± 0.18 | 0.77 ± 0.22 | 0.69 ± 0.16 | 0.79 ± 0.15 | 0.79 ± 0.15 | +2% | |
0.75 ± 0.22 | 0.76 ± 0.22 | 0.72 ± 0.17 | 0.76 ± 0.21 | 0.71 ± 0.18 | 0.73 ± 0.19 | 0.73 ± 0.19 | −3% | |
0.64 ± 0.07 | 0.65 ± 0.06 | 0.65 ± 0.06 | 0.72 ± 0.26 | 0.63 ± 0.08 | 0.73 ± 0.05 | 0.73 ± 0.05 | +7% | |
0.63 ± 0.13 | 0.50 ± 0.07 | 0.63 ± 0.13 | 0.63 ± 0.14 | 0.73 ± 0.16 | 0.63 ± 0.09 | 0.67 ± 0.11 | +4% | |
0.67 ± 0.16 | 0.67 ± 0.16 | 0.66 ± 0.16 | 0.67 ± 0.16 | 0.67 ± 0.16 | 0.63 ± 0.13 | 0.67 ± 0.14 | 0% | |
0.52 ± 0.09 | 0.53 ± 0.10 | 0.52 ± 0.10 | 0.52 ± 0.09 | 0.52 ± 0.09 | 0.56 ± 0.06 | 0.58 ± 0.06 | +3% | |
0.52 ± 0.09 | 0.53 ± 0.10 | 0.52 ± 0.10 | 0.52 ± 0.09 | 0.52 ± 0.09 | 0.56 ± 0.06 | 0.58 ± 0.06 |
Baseline Methods | Proposed Methods | ||||||
---|---|---|---|---|---|---|---|
Dataset | XGBoost [19] | RF [8] | SVM [39] | LR [19] | Att-bi-LSTM [10] | HDC-Based | Att-HDC |
0.82 | 0.82 | 0.82 | 0.82 | 0.82 | 0.049 | 0.049 | |
1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 0.051 | 0.051 | |
0.79 | 0.79 | 0.79 | 0.79 | 0.79 | 0.027 | 0.027 | |
0.80 | 0.82 | 0.78 | 0.82 | 0.82 | 0.021 | 0.021 | |
0.80 | 0.82 | 0.78 | 0.82 | 0.82 | 0.021 | 0.021 | |
0.80 | 0.82 | 0.78 | 0.82 | 0.82 | 0.021 | 0.021 | |
0.80 | 0.82 | 0.78 | 0.82 | 0.82 | 0.021 | 0.021 | |
0.80 | 0.82 | 0.78 | 0.82 | 0.82 | 0.021 | 0.021 | |
0.79 | 0.79 | 0.79 | 0.79 | 0.79 | 0.027 | 0.027 | |
0.78 | 0.78 | 0.78 | 0.78 | 0.78 | 0.028 | 0.028 | |
0.79 | 0.79 | 1.0 | 0.79 | 0.79 | 0.020 | 0.020 |
Dataset | RF | XGBoost | Att-bi-LSTM | HDC | Att-HDC |
---|---|---|---|---|---|
BPIC2012—Approved | 107 | 147 | 11 | 0.61 | 13 |
BPIC2012—Cancelled | 129 | 123 | 7 | 0.47 | 16 |
BPIC2012—Declined | 236 | 98 | 8 | 0.48 | 17 |
BPIC2015—1 | 21 | 101 | 108 | 0.16 | 0.16 |
BPIC2015—2 | 36 | 42 | 217 | 0.11 | 0.11 |
BPIC2015—3 | 29 | 33 | 134 | 0.5 | 0.5 |
BPIC2015—4 | 30 | 28 | 98 | 0.36 | 0.36 |
BPIC2015—5 | 33 | 17 | 124 | 0.62 | 8 |
BPIC2017—Approved | 143 | 112 | 217 | 14 | 36 |
BPIC2017—Cancelled | 204 | 183 | 187 | 5 | 29 |
BPIC2017—Declined | 181 | 154 | 219 | 11 | 35 |
BPIC2019 | 153 | 249 | 104 | 104 | 139 |
Average | 107.08 | 114.08 | 128.58 | 10.38 | 26.35 |
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2024 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Asgarinejad, F.; Thomas, A.; Hildebrant, R.; Zhang, Z.; Ren, S.; Rosing, T.; Aksanli, B. Optimized Early Prediction of Business Processes with Hyperdimensional Computing. Information 2024, 15, 490. https://doi.org/10.3390/info15080490
Asgarinejad F, Thomas A, Hildebrant R, Zhang Z, Ren S, Rosing T, Aksanli B. Optimized Early Prediction of Business Processes with Hyperdimensional Computing. Information. 2024; 15(8):490. https://doi.org/10.3390/info15080490
Chicago/Turabian StyleAsgarinejad, Fatemeh, Anthony Thomas, Ryan Hildebrant, Zhenyu Zhang, Shangping Ren, Tajana Rosing, and Baris Aksanli. 2024. "Optimized Early Prediction of Business Processes with Hyperdimensional Computing" Information 15, no. 8: 490. https://doi.org/10.3390/info15080490