# Getting high intent confidence for untrained bot utterances

**URL:** <https://forum.rasa.com/t/getting-high-intent-confidence-for-untrained-bot-utterances/47863>\
**Category:** Rasa Open Source\
**Created:** [September 20, 2021, 2:55pm UTC](https://forum.rasa.com/t/getting-high-intent-confidence-for-untrained-bot-utterances/47863 "2021-09-20T14:55:49Z")\
**Posts on this page:** 1\
**Showing post:** 1

<div class="post-metadata">

**Author:** ![simpleng](https://avatars.discourse-cdn.com/v4/letter/s/0ea827/32.png) [@simpleng](https://forum.rasa.com/u/simpleng)\
**Post date:** [September 20, 2021, 2:55pm UTC](https://forum.rasa.com/t/getting-high-intent-confidence-for-untrained-bot-utterances/47863/1 "2021-09-20T14:55:49Z")

</div>

Below is the config and nlu file content. Issue description: for any untrained utterances it is giving intent and with high confidence(0.99) Untrained utternaces like “cricket station” “Michael is on leave” “asdasfasf” PLease correct if any changes in config or nlu data file

Config file: language: en

pipeline:

- name: addons.CustomTokenizer.CustomTokenizer
- name: RegexFeaturizer case\_sensitive: true use\_word\_boundaries: false
- name: CountVectorsFeaturizer stop\_words:
  - a
  - and
  - any
  - are
  - aren’t
  - because
  - being
  - by
  - can’t
  - cannot
  - could
  - couldn’t
  - does
  - doesn’t
  - don’t
  - during
  - from
  - further
  - if
  - in
  - into
  - itself
  - let’s
  - more
  - of
  - or
  - other
  - ought
  - over
  - shan’t
  - some
  - such
  - than
  - that
  - that’s
  - them
  - themselves
  - this
  - those
  - through
  - under
  - until
  - up
  - very
  - where
  - where’s
  - which
  - while analyzer: word min\_ngram: 1 max\_ngram: 4

- name: DIETClassifier epochs: 100
- name: addons.FuzzyMatch.EntityTypoFixer score\_cutoff: 0.9
- name: FallbackClassifier threshold: 0.4 ambiguity\_threshold: 0.1
- name: EntitySynonymMapper

policies:

- name: TEDPolicy max\_history: 1 epochs: 150 batch\_size: 20 max\_training\_samples: 300
- name: MemoizationPolicy

nlu file version: ‘2.0’ nlu:

- intent: greetings\_how\_r\_u examples: '- how are you getting on

- intent: greetings\_hello examples: '- hi

- intent: hours\_min examples: '- what is the time now

- intent: month\_date examples: '- what date is it

---

_[View the full topic](https://forum.rasa.com/t/getting-high-intent-confidence-for-untrained-bot-utterances/47863)._