MétaCan
Menu
Back to cohort
Record W4362607906 · doi:10.1002/aaai.12079

Deploying automated ticket router across the enterprise

2023· article· en· W4362607906 on OpenAlex

Why this work is in the frame

A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.

affAt least one author lists a Canadian institution in the pinned OpenAlex snapshot.

Bibliographic record

VenueAI Magazine · 2023
Typearticle
Languageen
FieldComputer Science
TopicSoftware System Performance and Reliability
Canadian institutionsIBM (Canada)
Fundersnot available
KeywordsSoftware deploymentIBMTicketComputer scienceService (business)Perspective (graphical)Process managementEngineering managementKnowledge managementEngineeringArtificial intelligenceSoftware engineeringComputer securityBusinessMarketing

Abstract

fetched live from OpenAlex

Abstract With the recent advances in machine learning, the use of natural language processing (NLP) technology to support various business processes has been increasing. This paper discusses the use of NLP to route more than one million live client tickets annually to the appropriate service personnel in 67 support missions across IBM. Each mission supports a product family with multiple support teams, each requiring different skills for the engineers. We discuss three important aspects of such a large‐scale deployment: (i) The use of a centralized team with a common machine learning infrastructure and practices to support the entire enterprise. (ii) The processes and quality of such a deployment from the perspective of one support mission, namely, IBM's z/OS family. (iii) Careful monitoring of the deployed models to detect drifts in the routing behavior. Despite vast differences in the technical contents of the support missions, it is possible to define common processes and metrics across the enterprise, without requiring a dedicated machine learning team for each mission. In addition, we provide examples of the business policies and metrics from the perspective of the z/OS mission to demonstrate the utility of the approach and the outcome.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.001
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesInsufficient payload (model declined to judge)
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Not applicable · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.563
Threshold uncertainty score0.996

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0010.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.001
Science and technology studies0.0000.000
Scholarly communication0.0000.000
Open science0.0010.001
Research integrity0.0000.000
Insufficient payload (model declined to judge)0.0000.005

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.013
GPT teacher head0.293
Teacher spread0.280 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it