Adversus Blog: For call centers

Answering Machine Detection – Pros and Cons

Written by Line Jensen | Aug 27, 2021 12:32:10 PM

Answering machine detection has become a significant topic of concern in various countries, particularly in the UK, due to stringent regulations that are leading many outbound call centers to phase out the use of AMDs. However, the question remains: should this be a deterrent to using AMDs? Let's find out the answer right here.

 

What is answering machine detection?

Answering machine detection (AMD) is a valuable technology used in outbound call centers to optimize performance. It helps screen outgoing calls, identifying and bypassing voicemails and IVRs to save agent time.

When an answering machine is detected, the call can be either disconnected, or a message can be left on the voicemail.

While enabling AMD may seem like a good idea to boost performance and hit rates, there are some potential drawbacks you should be aware of before implementation.

One significant concern revolves around compliance issues, especially within the telemarketing industry. AMD can sometimes lead to silent or abandoned calls, which are regulated by law in certain countries. Failure to adhere to these regulations can result in substantial fines.

In the following discussion, we'll unfold this topic to ensure you are well-informed about the implications of using AMD in your call center operations.

 
Pro tip when using AMD

When there's a slight delay before the call connects to an agent, callers might say "hello, hello" and hang up. The key solution here is to advise your agents to swiftly start their pitch as soon as they get connected to make up for those lost seconds. This proactive approach can significantly improve engagement and reduce the chances of callers hanging up prematurely.

How does AMD work?

The main principle behind answering machine detection (AMD) lies in the AMD system's ability to listen to the initial seconds of a call and analyze the audio's sound patterns.

The AMD detects specific strings of words, the pauses or silence between words, and background noise or silence characteristic of answering machines. Alternatively, it detects human speech patterns, indicating that a person has answered the phone.

By differentiating between these audio patterns, the AMD system efficiently determines whether a call has connected to a live person or an answering machine.

What are the disadvantages of using AMDs?

During the audio analysis, a delay is introduced between the call being answered and its connection to an agent. The duration of this analysis can range from one to five seconds, depending on the algorithm and technology employed. However, this delay can lead to a potential issue known as a "false positive."

In a false positive scenario, the call recipient experiences a few seconds of silence before getting disconnected because the call never reaches an agent. This drawback stands as the primary disadvantage of utilizing AMD systems.

While AMD can be valuable for screening answering machines, it's essential to be mindful of the potential for false positives and consider its impact on the overall customer experience.

This is the primary disadvantage of using AMD systems.

 

False positives definition: When your AMD mistakes a human for a machine.

The recipient will receive a silent call for a few seconds and then get disconnected. It may confuse the recipient and result in losing a sales opportunity.

False negatives definition: When your AMD mistakes a machine for a human.

The call is answered by a machine, but the system detects it as a human. The recipient will never notice the mistake, nor is the false negative a disadvantage because the result is the same as not using AMD detection in the first place.

Can you avoid silent and abandoned calls?

The short answer is no.

There is always uncertainty in using the AMD technology, no matter how much you fine-tune your system. But fine-tuning and correct use can decrease both false positive and false negative calls and reduce the amount of silent and abandoned calls made.

You will get a few tips on how to fine-tune if you keep on reading.

 

Compliance issues

In certain countries, it's essential to exercise caution when using AMD unless you are well-versed in its proper implementation. For example, in the UK, AMDs have been a subject of debate due to the prevalence of silent or abandoned calls, which can leave people feeling uneasy, especially when the number is unknown.

Imagine receiving continuous hang-up calls from an anonymous number. Such situations can be quite intimidating for most people.

The issue has become so widespread that Ofcom, the UK regulator for communication services, has taken action to reduce the number of abandoned and silent calls. They stipulate that no more than three percent of calls can be abandoned, and if a call goes through but doesn't connect to an agent, a message must be left within two seconds.

Ofcom is also empowered to investigate cases where repetitive occurrences of such calls are suspected, and non-compliance with these regulations can result in fines of up to two million pounds. It's crucial to be aware of and adhere to the regulations to ensure responsible and lawful use of AMD technology.

Read more on how to handle GDPR in your contact center.

When is it a good idea to use AMD – and when is it bad?

Setting aside compliance issues, you will still find cases where AMD can harm your business. But there are also cases where AMD can be an efficient tool to optimize your sales flow. Let's dive into that.

B2B calling and AMD

By default, using AMD while calling B2B can be problematic since many B2B companies utilize interactive voice response (IVR) menus. When AMD detects these IVRs as machines, most calls will be hung up on, hindering your chances of reaching prospects.

However, if you are dialing small companies that do not have IVRs in place, it's worth reconsidering and possibly switching on the AMD. In such cases, the likelihood of connecting with a human during B2B calls is relatively high, making AMD an efficient tool to optimize your outreach. Evaluating your specific B2B calling scenario can help determine whether using AMD is a beneficial strategy for your business.

Using AMD calling B2C

B2C operations differ from B2B, as reaching customers can be more challenging, and campaigns may run throughout the entire day.

While using AMD in B2C campaigns can save time, it's crucial to tread carefully, considering the risk of annoying silent calls and potential compliance issues. Before enabling AMD, a thorough analysis of its necessity is strongly recommended. Avoid turning it on by default and instead assess how your campaign performs before deciding on its suitability.

Typically, AMDs are employed in large call centers where the lead pools allow for a certain number of dropped calls. The trade-off is justified by increased volume, leading to more successful connections.

Before enabling AMD, be prepared to accept and afford a certain level of wasted leads due to unavoidable false-positive or false-negative responses.

Analyze your data to understand the number of calls marked as "answering machines" and the time wasted, enabling informed decision-making.

Additionally, review the settings of your predictive dialer and make any necessary adjustments to ensure optimal performance and efficiency.

Learn more on how to choose the right autodialer for your business.

The AMD can be helpful in situations like this:
  • If you experience a relatively high volume of answering machines reached on your campaigns
  • If your predictive dialer is set to a high drop rate – in some cases, you can lower the drop rate by adding the AMD because the AMD picks up some of the dropped calls.
  • If you assign all unanswered calls (the ones where the chances of contacting the recipient in the first "go" are low) to a specific campaign, then the AMD can be an advantage.

Maybe it can come to your advantage not solely to focus on volume but also on the quality of the calls you make.

Are there any other ways to optimize your contact center success rate?

Segmenting your leads based on relevant criteria can help you target specific groups more effectively, increasing the chances of connecting with interested prospects.

Analyzing your contact history can provide valuable insights into the best times to call certain individuals or demographics, maximizing the likelihood of reaching them at a receptive moment.

Implementing call scheduling features within your call center software can enable you to time your calls strategically, improving the chances of connecting with live prospects and minimizing the instances of reaching answering machines.

By integrating these practices and utilizing data-driven strategies, you can enhance your efficiency and success in outbound calling, achieving similar or even better results without relying solely on AMD technology.

Some of this can be set up automatically based on data, so you don't need to waste time doing a lot of research before each call.

Can you use answering machine detection combined with caller ID?

Yes! It is possible.

Just ensure the recipient can call back to the correct number not to waste a good sales opportunity.

Can you use AMD without Predictive dialing?

Yes, you can.

But it is not recommended. With manual or progressive dialing, your agents can detect answering machines more accurately, avoiding false positives. Also, their productivity would not increase by using AMD.

Hidden number – is it a good idea when using AMDs?

Calling from an unknown or hidden number is uncommon in call centers nowadays. It has been recognized that using hidden numbers does not lead to a significant increase in picked-up calls.

We strongly advise against making silent calls or calls from secret numbers. Such practices can be annoying and even intimidating for recipients, as they have no way of knowing who made the call.

Instead, it's a good practice to set up your system to leave a pre-recorded message on the recipient's answering machine if the call goes unanswered. This way, the recipient will receive relevant information even if they missed the call, avoiding any confusion caused by unknown numbers.

By being transparent and courteous in your approach, you can improve the overall customer experience and ensure a more positive perception of your call center's outreach efforts.

How Accurate and Efficient is AMD Technology?

There is no such thing as a bulletproof AMD solution with a 100 percent success rate, but you can get close to 100 percent success by using it correctly and tuning it the right way. And indeed, you don't want to miss a great sales opportunity.

To make the most of AMD, it's essential to understand how it works and when to implement it. Basic knowledge of AMD technology is crucial for optimizing its performance and reducing dropped calls.

Additionally, pay close attention to your predictive dialing settings. Ensuring that they are appropriately adjusted can help prevent dropped calls and improve the overall efficiency of your calling campaigns.

By continually monitoring and fine-tuning your AMD system, you can maximize its effectiveness, increase your chances of connecting with live prospects, and ultimately boost your sales success.

How to detect false positive and false negative calls using AMD in your call center

To detect false negatives, you may rely on your agents' feedback when they start to receive too many transferred calls that prove to be machined.

By manually monitoring and listening to a sample database of calls, you can get a more precise idea of the accuracy. Once you have this data, you can extrapolate the results to a larger dataset to get an approximate statistic for the overall performance of the AMD.

To validate your findings further, compare your AMD results to industry averages. If you notice significant discrepancies between your AMD's performance and the expected industry standards, it's crucial to investigate and fine-tune your system accordingly.

By continually evaluating and improving your AMD system, you can ensure that it accurately identifies answering machines while minimizing false negatives and enhancing the overall efficiency of your outbound calling campaigns.

Adversus' AMD solution

At Adversus, we use a proprietary algorithm that can be constantly monitored, adapted, and fine-tuned for each country and language.

Most solutions do not consider localization and language but use a general configuration without considering that each country and network operator has various voicemail types and that real people answer calls differently. How people answer their phones also depends on their culture and spoken language!

Our goal is to have as close to 100 percent for human detection (no false positives) while filtering as many machines as possible.

Is it possible to leave a prerecorded message on the answering machine while using Adversus?

Yes, it is.

Our system can detect the answering machine with the AMD, wait for the "beep" or voicemail introduction to end, and then playback the prerecorded message.

What precautions has Adversus made to prevent silent and abandoned calls?

Our system allows customers to playback introduction audio and/or IVR to the callee to prevent silent calls.

We constantly monitor the ratio of detected answering machines and cross-reference it with recordings of calls and global industry statistics. If the ratio gets higher or below our QoS, we immediately correct its performance, thus preventing the maximum number of silent and abandoned calls.

When does Adversus recommend using AMD?

On all B2C predictive campaigns that want to perform at it's best, we recommend using AMD. On average, two out of three outbound contact center calls get answered by a machine or voicemail.

By combining our Predictive and AMD technology, your agents can be up to 350 percent more productive.

Read more on how  Adversus can help you improve your business. 

 

 Advantages
  • The AMD is an overall time saver and a great tool to optimize performance.
  • You can enhance the volume of calls made 
  • You minimize frustrations among your agents because the chances of making successful calls get higher.
Disadvantages
  • You risk giving a bad customer experience by making silent and abandoned calls.
  • You may miss out on some sales when you get false positives and negatives.
  • It is harder to do responsible dialing and keep up with compliance.
  • Under some regulations, you risk getting fined if you do not live up to them.
  • You need to fine-tune your predictive algorithm, and your dialer needs to work in real time before you can take advantage of AMD.
  • It's most commonly not a good tool if you are calling B2B.
  • Your lead pools must have a considerable volume before it pays off to use AMD. If your lead pool is small, the risk of wasting good leads gets too high when using AMD.
  • It's not suitable for manual and progressive calling.

Sources: