Average Handle Time Optimization study

Challenge:

With over 5 million customer base across its versatile profile that includes personal and commercial banking, life insurance, loans, and credit cards, a leading American bank was overwhelmed by its raising AHT at their call centers, despite believing to be the best at providing automated solutions to its customers, the client was worried to see the higher number of long interactions which was costing them more than anticipated for last 3 quarters. They asked MattsenKumar to look out for the core reasons for such long calls and help them eliminate the causes by the next quarter, a quick study was required to be performed within a timeframe of 2 weeks using a random sample of long calls.

  • Identify top contributors to High AHT
  • Identify Non-Talk-Time/ Mute (silence) instances at the organizational level
  • Provide AHT information and related insights by Agent tenure (0-3 months, 3-6 months, 6-12 months, more than a Year)
  • Contribution of long calls in the overall data for the given time period
  • Identify the site/s with most AHT

Customer Profile:

An American multinational bank, with more than 100+ years of experience in banking and financial domain, around the world, providing consumers, corporations, and institutions with a broad range of financial products and services, including consumer banking and credit, corporate and investment banking, securities brokerage and wealth management, etc.

  • of Agents: 1500+
  • 5 sites (A, B, C, D, E)
  • 500k calls/ month

Our Approach:

The project was guided by the following set of broadly stated objectives:

  • Ingested a sample of 99k calls, across 3 sites in focus (A, B, C), call type was “Banking” only
  • Agents in focus: 305, Language in scope: English
  • Filtered the results with calls between 15-30 mins on the speech platform and extracted the results for further analysis
  • SmartSpeech POD listened to a sample of 300 random calls (100 on each side) from their banking customer service domain to determine its core call drivers and AHT related opportunity areas
  • SmartSpeech POD prepared the required number of call driver queries and created related reports on the SmartSpeech Analytics platform
  • SmartSpeech team tracked further interesting elements on these call drivers through an exercise of hypothesis validation and shared the insights providing additional value to the client
  • Listed the actionable recommendations based on the opportunities identified to improve the current situation and processes

Our Solution:

SmartSpeech team identified that Site B had the highest number of interactions between 15-30 mins bucket and was producing the highest number of Non-Talk events as well over the calls, these NTT events are caused by practices like Incorrect Hold procedure, Long MUTE intervals, etc. and can be rectified with proper coaching and mentoring. The biggest outliers were identified to be the agents falling under 0-3 months of work tenure across all 3 sites in focus.

Our SmartSpeech POD discovered many call drivers which affected their existing call flow from a higher handle time perspective and here are the top 5 categories:

  • PIN Generation (19%)
  • Debit Card Hotlisting (15%)
  • Digital Banking enrolment (13%)
  • Unknown charges on account (10%)
  • Fixed deposit inquiry/request (8%)

SmartSpeech team not only identified the top core call reasons behind high AHT but however also prepared relative queries in the system, this will help the client to utilize the speech analytics platform to the fullest as these queries not only just showcase the latest results for a certain topic but also let the user/ analysts play with the platform’s reporting capabilities effectively, the users can now also export the data and apply various permutation and combinations through it to derive more complex and useful results. SmartSpeech team has identified the Organizational AHT to be 960 seconds and NTT at 21%, and site B was discovered to be handling long calls the most for call drivers like Cheque book request (15%), Unknown account charges (12%), and Debit card Hotlisting (9%) topping the charts among other sites. 26% of agents (0-3 months’ tenure) were identified placing the customers on long holds and seem to place several MUTE intervals, which is translated as incorrect hold procedure.

Results:

In just 2 weeks, the list of all identified call drivers for higher AHT was shared successfully with the client, required reports were prepared as well for future reference. The consolidated list of other related challenges and recommendations was also shared as a value add. AHT has decreased by 12% resulting in a benefit estimated at $1.04m, MattsenKumar not only provided the results at the earliest but also proven to be the best at delivering value utilizing the speech analytics platform.