• Images
• Videos
• Documents
• Books
• Articles

Examples and real world applications

Data shows that a large percentage of users using a certain eCommerce platform found it by searching for “Thai food” on Google. After landing on the homepage, most people spent some time on the “Asian Food” page and then logged off without placing an order. Looking at each of these events as separate data points does not represent what is really going on and why people did not make a purchase. However, viewing these data points as a representation of overall user behavior enables one to interpolate how and why users acted in this particular case.

Behavioral analytics looks at all site traffic and page views as a timeline of connected events that did not lead to orders. Since most users left after viewing the “Asian Food” page, there could be a disconnect between what they are searching for on Google and what the “Asian Food” page displays. Knowing this, a quick look at the “Asian Food” page reveals that it does not display Thai food prominently and thus people do not think it is actually offered, even though it is.

Behavioral analytics is popular in commercial environments. Amazon.com is a leader in using behavioral analytics to recommend additional products that customers are likely to buy based on their previous purchasing patterns on the site.⁵ Behavioral analytics is also used by Target to suggest products to customers in their retail stores, while political campaigns use it to determine how potential voters should be approached. In addition to retail and political applications, behavioral analytics is also used by banks and manufacturing firms to prioritize leads generated by their websites. Behavioral analytics also allow developers to manage users in online-gaming and web applications.⁶

Amongst others, IBM and Intel are creating advanced analytics solutions. In retail, this is IoT for tracking shopping behaviors (in-store tracking).⁷⁸

Types

• Ecommerce and retail – Product recommendations and predicting future sales trends
• Online gaming – Predicting usage trends, load, and user preferences in future releases
• Application development – Determining how users use an application to predict future usage and preferences.
• Cohort analysis – Breaking users down into similar groups to gain a more focused understanding of their behavior.
• Security – Detecting compromised credentials and insider threats by locating anomalous behavior.
• Suggestions – People who liked this also liked...
• Presentation of relevant content (preferences, user groups, etc.) based on user behavior.⁹

Components

An ideal behavioral analytics solution would include:

• Real-time capture of vast volumes of raw event data across all relevant digital devices and applications used during sessions
• Automatic aggregation of raw event data into relevant data sets for rapid access, filtering and analysis
• Ability to query data in an unlimited number of ways, enabling users to ask any business question
• Extensive library of built-in analysis functions such as cohort, path and funnel analysis
• A visualization component

See also

• Analytics
• Big data
• Business intelligence
• Business process discovery
• Cohort analysis
• Customer dynamics
• Data mining
• Funnel analysis
• Path analysis
• Personalized marketing
• Test and learn
• Web tracking

Further reading

• Nagaitis, Mark. "Behavioral Analytics: The Why and How of E-Shopping". eCommerce Times.

• LeClaire, Jennifer. Rushin, Jason. "Behavioral Analytics For Dummies". Z-Library.

References

1. Shah, Saleh, et al. "Compromised user credentials detection in a digital enterprise using behavioral analytics." Future Generation Computer Systems 93 (2019): 407-417. https://zuscholars.zu.ac.ae/cgi/viewcontent.cgi?article=2004&context=works ↩

2. Yamaguchi, Kohki (6 June 2013). "Leveraging Advertising Data For Behavioral Insights". Analytics & Marketing Column. Marketing Land. http://marketingland.com/leveraging-advertising-data-for-behavioral-insights-46467 ↩

3. Biddle, Sam (2019-05-20). "Thanks to Facebook, Your Cellphone Company Is Watching You More Closely Than Ever". The Intercept. Retrieved 2019-07-01. https://theintercept.com/2019/05/20/facebook-data-phone-carriers-ads-credit-score/ ↩

4. "Goodbye, Chrome: Google's web browser has become spy software". The Washington Post. https://www.washingtonpost.com/technology/2019/06/21/google-chrome-has-become-surveillance-software-its-time-switch/ ↩

5. "Oh behave! How behavioral analytics fuels more personalized marketing" (PDF). Archived from the original (PDF) on 2014-07-14. https://web.archive.org/web/20140714180534/http://public.dhe.ibm.com/common/ssi/ecm/en/zzw03004usen/ZZW03004USEN.PDF ↩

6. "Oh behave! How behavioral analytics fuels more personalized marketing" (PDF). Archived from the original (PDF) on 2014-07-14. https://web.archive.org/web/20140714180534/http://public.dhe.ibm.com/common/ssi/ecm/en/zzw03004usen/ZZW03004USEN.PDF ↩

7. Gupta, Deepak (2021-12-08). "Council Post: In-Store Tracking: Is It A Threat To Consumer Privacy?". Forbes. Retrieved 2023-02-20. https://www.forbes.com/sites/forbestechcouncil/2021/12/08/in-store-tracking-is-it-a-threat-to-consumer-privacy/ ↩

8. Max, Ronny (2021-10-27). "19 Technologies of People Tracking". Behavior Analytics Retail. Retrieved 2023-02-20. https://behavioranalyticsretail.com/technologies-tracking-people/ ↩

9. Behrooz Omidvar-Tehrani; Sihem Amer-Yahia; Alexandre Termier (2015). "Interactive User Group Analysis". Proceedings of the 24th ACM International on Conference on Information and Knowledge Management. International Conference on Information and Knowledge Management (CIKM) 2015. pp. 403–412. doi:10.1145/2806416.2806519. ISBN 9781450337946. S2CID 7675754. 9781450337946 ↩