Cut support costs with a window into contact center dark data
Key points to unlocking your customer service dark data:
- Contact center is the heart of your customer conversations where brand loyalty relationships can be built or broken costing $9.7 million/year due to bad data
- True cost of bad data: customer churn, agent attrition, & operational efficiency & time
- Simplify the complexity to understanding your conversational data customer service topics and reasons to improve customer service
What does customer service have to do with dark data?
- Language data exists in vast quantities across the digital world but hasn’t traditionally been a source of insight
- Customer service unstructured dark data examples: call-center transcripts, text messages, survey responses, customer reviews, emails, documents, and more
- The challenge: bringing order to the chaos of dark data problems—too much data, inaccurate data, & poor data quality
- Example of challenge: manual review of transcript data that costs you time and resources
- Example of solution: simplified and automated process to understand your contact center conversations and customer service topics across channels with your agents and bots
- The result: data sources become functional & insightful to improve customer service vs. dead weight
![](https://cdn.prod.website-files.com/663297b3eea9bb42e92772bf/663297b3eea9bb42e92776df_zT_2ZgUEiQBsSLD91TLf_CLCxE3-cp6pEPTXizXCwZTIxXn8nuSe6SFavv0yy4W-GruTX37CCmBbYbvXM2Q2pZlNgPlhWFqSaZdKpIh0mrx50h4H8VMUJp2hwy53mrL0ykW8XZ6ZCmb8BfAg0cVKlYE.png)
Simplifying Data Complexity
Unstructured dark data source example chat transcript
![](https://cdn.prod.website-files.com/663297b3eea9bb42e92772bf/663297b3eea9bb42e92776dc_ygJaHTcez1-fA19j-FXTsI1oEErqbnIYBnIjxfCvhJjqR0S2Vy5oH-CUIT6kTEnoqIacjQDyoB16SzMXuHo0c7Okvb6MLQ2CGVUGwokXlseu0C50i_9y3phDQvNQhF-Rdqx3TmnpUN-0aEMfdRypjOM.png)
Chat transcript -> customer service topics
![](https://cdn.prod.website-files.com/663297b3eea9bb42e92772bf/663297b3eea9bb42e92776de_rJe1O6sU6JGgd0DDKygllg0jskn_N65U-FEZpp7rWItRcM4FP7F5m6lGK5TEGfVXlRbe2Vi9LfiI_Y_ovxfu3QEtJAVyf9qTvt2LqtQFBVlUZehsSg8r9wnYwLHnxZqInxIjH6H4BZywhZKaV1Zqhwc.png)
Chat transcripts -> customer service topics -> reason
![](https://cdn.prod.website-files.com/663297b3eea9bb42e92772bf/663297b3eea9bb42e92776e0_bxsptquPQSUFCaxJ_j3AnDqnx01p9sGsa35T4LvlwhW5gqumJqmUvv-Zt4yP-QJFeCOP6xHWp-ezv6jCj78BxEHm56nLsGx8HIdv-bk5CYfF1KXBdPJ8juX0Ld_Q8rcbtS-BBPTwCEiLk7-eu9H8rUU.png)
Balancing NLP & Prompt Engineering
Constraints of solely relying on prompt engineering are cost & precision:
- Bound by API constraints (e.g. limited adjustable parameters, guardrails imposed by creators, compute time - e.g. 20 seconds per prompt)
- Prompt engineering isn't a solved problem and may not be fully optimizable in principle due to the natural language format
- Traditional NLP methods offer precise control over pipeline/output + are more optimal in some cases (e.g. topic clustering for vectors)
Harmonizing prompt engineering + traditional NLP methods based on what is optimal. Example workflow:
- Vectorize language data
- Cluster into topics
- Feed topic data into prompts for label creation
![](https://cdn.prod.website-files.com/663297b3eea9bb42e92772bf/663297b3eea9bb42e92776dd_-DF5wJrSVr32PXvRsC9SncvhSXSGmlBTSAs7dEwV2oNrWN7paGkDx0NHgZQ6Yi_kic4ODTvN58ofukH8erDyeXSUDUkUnLf1YoTb44PEs_98-9Za2BuOE3qbevushAwzvCGWncMWrrjLk5Tpz6w6-aQ.png)
![](https://cdn.prod.website-files.com/663297b3eea9bb42e92772bf/663297b3eea9bb42e92776e1_JXJK8NtxyKSZGhtvNBO2FAjbP41MLw-wlPOWJjP57R45sisGqRv_DdrnazcDKG0WKH7lGTTOnmaJ-AHA4JliiuJQSPOj-gIReiuXs19Q6YaEtOoLZwK2Zb8KEE2caYLzQOtgyxK6cgWszRD1efEb8pc.png)