Session monitoring for selective intervention

1. A network computer system comprising:

one or more processors;

a memory to store a set of instructions;

wherein the one or more processors access the set of instructions to: detect, from monitoring a website in a given time interval, multiple users of an unknown classification that each perform an initiating event to access the website;

for each of the multiple users, record one or more events that follow the initiating event in sequence, the recorded sequence of events reflecting a series of activities the user performed to access the website;

based at least in part on the recorded sequence of events, make a determination as to whether the user is (i) firm in their intent, such that an outcome of the user's activities with respect to the website is not likely to be influenced through intervention, or (ii) likely to be influenced into a-performing a desired action through intervention;

for at least one of the multiple users for whom the determination is that the user is likely to be influenced, select a particular intervention that is more likely to cause the user to perform the desired action; and

trigger the particular intervention to the selected user.

2. The network computer system of claim 1 , wherein for each of the multiple users, the one or more processors record a set of attributes with each event of the recorded sequence of events.

3. The network computer system of claim 2 , wherein for each of the multiple users, the set of attributes include one or more attributes that reflect an item that was a subject of a user activity of the series of activities that the user performed.

4. The network computer system of claim 2 , wherein for each of the multiple users, a recorded event of the recorded sequence of events includes at least one of (i) a device type for an end user device, (ii) a browser of the end user device, and/or (iii) information provided with an initial request to access a web resource of the website in an initial visit.

5. The network computer system of claim 2 , wherein for each of the multiple users, a recorded event of the recorded sequence of events includes at least one of a geographic origin or network origin of the user.

6. The network computer system of claim 1 , wherein the one or more processors implement a predictive model to make the determination for each of the multiple users.

7. The network computer system of claim 1 , wherein the one or more processors select the particular intervention based on an intervention type.

8. The network computer system of claim 1 , Wherein the particular intervention corresponds to a communication displayed on a device of each selected user.

9. The network computer system of claim 1 , wherein the particular intervention corresponds to a promotional offer made to each selected user.

10. The network computer system of claim 1 , wherein the desired action corresponds to a conversion action.

11. A non-transitory computer-readable medium that stores instructions, which when executed by one or more processors of a network computer system, cause the network computer system to perform operations that include:

detecting, from monitoring a website in a given time interval, multiple users of an unknown classification that each perform an initiating event to access the website;

for each of the multiple users, recording one or more events that follow the initiating event in sequence, the recorded sequence of events reflecting a series of activities the user performed to access the website;

based at least in part on the recorded sequence of events, making a determination as to whether the user is (i) firm in their intent, such that an outcome of the user's activities with respect to the website is not likely to be influenced through intervention, or (ii) likely to be influenced into performing a desired action through intervention;

for at least one of the multiple users for whom the determination is that the user is likely to be influenced, selecting a particular intervention that is more likely to cause the user to perform the desired action; and

triggering the particular intervention to the selected user.

12. The non-transitory computer readable medium of claim 11 , wherein each of the multiple users, recording the one or more events includes recording a set of attributes with each event of the recorded sequence of events.

13. The non-transitory computer readable medium of claim 12 , wherein for each of the multiple users, the set of attributes include one or more attributes that reflect an item that was a subject of a user activity of the series of activities that the user performed.

14. The non-transitory computer readable medium of claim 12 , wherein for each of the multiple users, a recorded event of the recorded sequence of events includes at least one of (i) a device type for an end user device, (ii) a browser of the end user device, and/or (iii) information provided with an initial request to access a web resource of the website in an initial visit.

15. The non-transitory computer readable medium of claim 12 , wherein for each of the multiple users, a recorded event of the recorded sequence of events includes at least one of a geographic origin or network origin of the user.

16. The non-transitory computer readable medium of claim 11 , wherein the instructions include instructions, which when executed by the one or more processors, cause the network computer system to perform operations that include implementing a predictive model to make the determination for each of the multiple users.

17. The non-transitory computer readable medium of claim 11 , wherein the particular intervention is selected based on an intervention type.

18. The non-transitory computer readable medium of claim 11 , wherein the particular intervention corresponds to a communication displayed on a device of each selected user.

19. The non-transitory computer readable medium of claim 11 , wherein the particular intervention corresponds to a promotional offer made to each selected user.

20. A method for operating a network computer system, the method being implemented by one or more processors and comprising:

detecting, from monitoring a website in a given time interval, multiple users of an unknown classification that each perform an initiating event to access the website;

for each of the multiple users, recording one or more events that follow the initiating event in sequence, the recorded sequence of events reflecting a series of activities the user performed to access the website;

based at least in part on the recorded sequence of events, making a determination as to whether the user is (i) firm in their intent, such that an outcome of the user's activities with respect to the website is not likely to be influenced through intervention, or (ii) likely to be influenced into performing a desired action through intervention;

for at least one of the multiple users for whom the determination is that the user is likely to be influenced, selecting a particular intervention that is more likely to cause the user to perform the desired action; and

triggering the particular intervention to the selected user.