customer_support · workflow

Monzo applies Recurrent Neural Networks to predict customer support questions and detect signup fraud

Monzo's two-person data team had many promising machine learning applications to evaluate but traditional methods required weeks of data manipulation before a model could be trained, making rapid experimentation impractical.

How it works
Common implementation structure
How this type of workflow is generally built, generalized across documented cases — not tied to any one vendor's stack. Click any stage to read what happens there. Specific products that implement these stages appear in “Tools commonly seen” below.
Stage 1 · User app events recorded
User actions within the app are recorded as an event time series.
Tools used
GRUTFLearnTensorflow
Outcome

RNNs achieved 30% top-1 and 53% top-3 accuracy predicting customer support question categories, and detected 40% of fraudulent accounts with a 42% false discovery rate. New ideas can now be tested in one or two days, more than ten times quicker than manually designing signals.

What failed first

A traditional data exploration approach to fraud detection — manually constructing features and looking at correlations — failed because of too much noise in the data and difficulty finding time-based patterns.

Results
Time savedone or two days
Volume30%
Cost replaced40%
Source

https://monzo.com/blog/2017/05/03/practical-machine-learning-for-startups

How we source this →

Grounding & classification
Source type: technical build writeup
23 fields verified against source quotes, 1 dropped as unverifiable.
fraud detectionpredictive analyticssupport ticketfailure mode describedmetric backednamed customertools describedworkflow describedbankingaccuracy improvementcycle time reductionemployee productivitytechnical build writeupcustomer supportkyc amlextract classify route