Abstract
Despite the ever-increasing enthusiasm from the industry, artificial intelligence or machine learning is a much-hyped area where the results tend to be exaggerated or misunderstood. Many novel models proposed in research papers never end up being deployed to production. The goal of this paper is to highlight four important aspects which are often neglected in real-world machine learning projects, namely Communication, Objectives, Deliverables, Evaluations (CODE). By carefully considering these aspects, we can avoid common pitfalls and carry out a smoother technology transfer to real-world applications. We draw from a priori experiences and mistakes while building a real-world online advertising platform powered by machine learning technology, aiming to provide general guidelines for translating ML research results to successful industry projects.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
Notes
- 1.
- 2.
- 3.
Adding more languages will actually inflate the average accuracy because most other languages can be easily identified by looking at the character alone and have an accuracy close to 1 (e.g. Chinese, Korean).
- 4.
References
Bagherjeiran, A., Tang, R., Zhang, Z., Hatch, A., Ratnaparkhi, A., Parekh, R.: Adaptive targeting for finding look-alike users. US Patent 9,087,332, 21 July 2015
Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly learning to align and translate. arXiv preprint arXiv:1409.0473 (2014)
Barker, J., Watanabe, S., Vincent, E., Trmal, J.: The fifth ‘CHiME’ speech separation and recognition challenge: dataset, task and baselines. arXiv preprint arXiv:1803.10609 (2018)
Boyko, A., Harchaoui, Z., Nedelec, T., Perchet, V.: A protocol to reduce bias and variance in head-to-head tests. Criteo Internal Report (2015)
Brooks, F.P.: The mythical man-month. Datamation 20(12), 44–52 (1974)
Enam, S.Z.: Why is machine learning ‘hard’? (2016). http://ai.stanford.edu/~zayd/why-is-machine-learning-hard.html. Accessed 10 Sept 2018
Goodfellow, I., Bengio, Y., Courville, A., Bengio, Y.: Deep Learning, vol. 1. MIT press, Cambridge (2016)
Hermann, J., Del Balso, M.: Scaling machine learning at uber with michelangelo (2018). https://eng.uber.com/scaling-michelangelo/
Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735–1780 (1997)
Jin, Y., Wanvarie, D., Le, P.: Combining lightly-supervised text classification models for accurate contextual advertising. In: Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 1: Long Papers), vol. 1, pp. 545–554 (2017)
Juan, Y., Lefortier, D., Chapelle, O.: Field-aware factorization machines in a real-world online advertising system. In: Proceedings of the 26th International Conference on World Wide Web Companion, pp. 680–688. International World Wide Web Conferences Steering Committee (2017)
Modi, A.N., et al.: TFX: a tensorflow-based production-scale machine learning platform. In: KDD 2017 (2017)
Ng, A.: AI transformation playbook: how to lead your company into the AI era (2018). https://landing.ai/ai-transformation-playbook/
Pappas, N., Popescu-Belis, A.: Multilingual hierarchical attention networks for document classification. arXiv preprint arXiv:1707.00896 (2017)
Perlich, C., Dalessandro, B., Hook, R., Stitelman, O., Raeder, T., Provost, F.: Bid optimizing and inventory scoring in targeted online advertising. In: Proceedings of the 18th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 804–812. ACM (2012)
Peterson, L.E.: K-nearest neighbor. Scholarpedia 4(2), 1883 (2009)
Pfister, R., Janczyk, M.: Confidence intervals for two sample means: calculation, interpretation, and a few simple rules. Adv. Cogn. Psychol. 9(2), 74 (2013)
Polyzotis, N., Roy, S., Whang, S.E., Zinkevich, M.: Data management challenges in production machine learning. In: Proceedings of the 2017 ACM International Conference on Management of Data, pp. 1723–1726. ACM (2017)
Qu, Y., et al.: Product-based neural networks for user response prediction. In: 2016 IEEE 16th International Conference on Data Mining (ICDM), pp. 1149–1154. IEEE (2016)
Raeder, T., Stitelman, O., Dalessandro, B., Perlich, C., Provost, F.: Design principles of massive, robust prediction systems. In: Proceedings of the 18th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 1357–1365. ACM (2012)
Russakovsky, O., et al.: ImageNet large scale visual recognition challenge. Int. J. Comput. Vis. (IJCV) 115(3), 211–252 (2015). https://doi.org/10.1007/s11263-015-0816-y
Sculley, D., Phillips, T., Ebner, D., Chaudhary, V., Young, M.: Machine learning: the high-interest credit card of technical debt (2014)
Shearer, C.: The CRISP-DM model: the new blueprint for data mining. J. Data Warehous. 5(4), 13–22 (2000)
Shi, L., Mihalcea, R., Tian, M.: Cross language text classification by model translation and semi-supervised learning. In: Proceedings of the 2010 Conference on Empirical Methods in Natural Language Processing, pp. 1057–1067. Association for Computational Linguistics (2010)
Sra, S., Nowozin, S., Wright, S.J.: Optimization for Machine Learning. MIT Press, Cambridge (2012)
Thomas, R.: What do machine learning practitioners actually do? (2018). http://www.fast.ai/2018/07/12/auto-ml-1/. Accessed 10 Sept 2018
Yuan, Y., Wang, F., Li, J., Qin, R.: A survey on real time bidding advertising. In: 2014 IEEE International Conference on Service Operations and Logistics, and Informatics (SOLI), pp. 418–423. IEEE (2014)
Acknowledgement
The first author is supported the scholarship from “The 100\(^{th}\) Anniversary Chulalongkorn University Fund for Doctoral Scholarship” and also “The 90\(^{th}\) Anniversary Chulalongkorn University Fund (Ratchadaphiseksomphot Endowment Fund)”. We would like to thank Assoc. Prof. Peraphon Sophatsathit and the anonymous reviewers for their careful reading and their insightful suggestions.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Jin, Y., Wanvarie, D., Le, P.T.V. (2019). Bridging the Gap Between Research and Production with CODE. In: Yang, Q., Zhou, ZH., Gong, Z., Zhang, ML., Huang, SJ. (eds) Advances in Knowledge Discovery and Data Mining. PAKDD 2019. Lecture Notes in Computer Science(), vol 11441. Springer, Cham. https://doi.org/10.1007/978-3-030-16142-2_22
Download citation
DOI: https://doi.org/10.1007/978-3-030-16142-2_22
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-16141-5
Online ISBN: 978-3-030-16142-2
eBook Packages: Computer ScienceComputer Science (R0)