Increase Marketing ROI with Multi-touch Attribution Modelling

With using Multi-touch Attribution Modelling advertisers typically realize a 15% – 44% improvement in marketing ROI with advanced multi-channel machine-learning algorithm. Using advanced machine learning techniques for marketing can give you true insight on performance all down to channel, campaign and device-level.

Implementing advanced machine learning models for marketing attribution will give you the following advantages:

  • Data-driven multi-touchpoint attribution.
  • Transparent and neutral: agency-independent and media-independent.
  • Connect the results of every touchpoint and campaign to your revenue stream.
  • Calculate the total cost of individual marketing campaigns to determine your ROI per campaign.
  • Channel-neutral: we evaluate both online and offline marketing channels and campaigns.
  • Budget optimiser to maximize your marketing ROI

Even small adjustments can have a noticeable effect on your marketing effectiveness and marketing ROI. With our Attribution Modelling machine learning model, we make the seemingly-complicated task of tracking the monetary impact of every touchpoint, every channel and every campaign easy. We can combine online and offline customer journeys and touchpoints to give you the full picture.

Non AI attribution modeling approaches

 undefined The Last Action Click model attributes 100% of the conversion value to the most recent Action ad that the customer clicked before buying or converting.

When it’s useful: If you want to identify and credit the Action that closed the most conversions, use the Last Action Click model.

undefined The First Interaction model attributes 100% of the conversion value to the first channel with which the customer interacted.

When it’s useful: This model is appropriate if you run ads or campaigns to create initial awareness. For example, if your brand is not well known, you may place a premium on the keywords or channels that first exposed customers to the brand.

 undefined The Linear model gives equal credit to each channel interaction on the way to conversion.

When it’s useful: This model is useful if your campaigns are designed to maintain contact and awareness with the customer throughout the entire sales cycle. In this case, each touchpoint is equally important during the consideration process.

 If the sales cycle involves only a short consideration phase, the Time Decay model may be appropriate. This model is based on the concept of exponential decay and most heavily credits the touchpoints that occurred nearest to the time of conversion. The Time Decay model has a default half-life of 7 days, meaning that a touchpoint occurring 7 days prior to a conversion will receive 1/2 the credit of a touchpoint that occurs on the day of conversion. Similarly, a touchpoint occuring 14 days prior will receive 1/4 the credit of a day-of-conversion touchpoint. The exponential decay continues within your lookback window (default of 30 days).

When it’s useful: If you run one-day or two-day promotion campaigns, you may wish to give more credit to interactions during the days of the promotion. In this case, interactions that occurred one week before have only a small value as compared to touchpoints near the conversion.

  The Position Based model allows you to create a hybrid of the Last Interaction and First Interaction models. Instead of giving all the credit to either the first or last interaction, you can split the credit between them. One common scenario is to assign 40% credit each to the first interaction and last interaction, and assign 20% credit to the interactions in the middle.

When it’s useful: If you most value touchpoints that introduced customers to your brand and final touchpoints that resulted in sales, use the Position Based model.

Stepping away from simplistic models like Last Click lets you take into account the full customer journey and properly account for all your marketing investments.

A Last Click attribution model leads to overvaluing and undervaluing certain channels, while Markov models – which take into account the full customer journey – is far more accurate. Using a good attribution model that takes into account the full customer journey lets you optimise marketing decisions based on the most valuable touchpoints.With Windsor.ai’s Attribution insights solutions, backed by a team of experienced data scientists who honed their craft at well-known multinational corporations. We extract valuable insights and recommendations so you can take action where it matters most to increase your MROI.

Algorithmic multi channel attribution

Here we take more in detail about how I use Machine Learning modeling to build multi channel attribution models.

multi-channel marketing graph with probabilities.png

Using machine learning models we can develop many models for comparing, such as Last Click, First Click, Linear, and the algorithmic Markov model to deliver the right solution for you, in the way that suits you best. This gives you the best possible understanding of your strongest and weakest customer touchpoints, so you can optimize them for maximum effect.

Leave a Reply

This site uses Akismet to reduce spam. Learn how your comment data is processed.