Documenti full-text disponibili:
|
Documento PDF (Thesis)
Disponibile con Licenza: Salvo eventuali più ampie autorizzazioni dell'autore, la tesi può essere liberamente consultata e può essere effettuato il salvataggio e la stampa di una copia per fini strettamente personali di studio, di ricerca e di insegnamento, con espresso divieto di qualunque utilizzo direttamente o indirettamente commerciale. Ogni altro diritto sul materiale è riservato
Download (1MB)
|
Abstract
Every marketer, at one time or another, has wondered when the perfect time to send emails is. Are recipients more likely to open messages in the morning or late at night? What about on Tuesdays at the lunchtime hour?
This problem is called Time Sent Optimization (TSO). Why is it so important?
Because it allows marketers to send emails at the optimal time for each contact. Also, it helps marketers engage more effectively with contacts, gaining contacts' attention when they are historically most attentive to their emails. Moreover, suppose that you want to start an advertising campaign. The more emails will be opened, the more the company will gain in terms of money and it will be easier for them to advertise some product. Not only, we do not want just to increase the open ratio, we also make sure that the user reads it. This translates is clicking the email, like scrolling it or clicking on links present in it.
Most of the medium and big companies already use Time Sent Optimization for the reasons explained before. However, they do not publish how they did that because of business reasons. If someone would publish a way of doing this, then everyone will copy it and then the purpose of doing this will be useless because it is likely that at a certain time, each user, will receive a lot of emails from several companies and this would lead ruin the benefit of TSO.
In this thesis, we take into account the case of a company called Diennea which gave us their data to improve their open and click ratio on the communications they send to their users. At the end, through online A/B test results, we show the effectiveness of our proposed approach and how to further improve it.
Abstract
Every marketer, at one time or another, has wondered when the perfect time to send emails is. Are recipients more likely to open messages in the morning or late at night? What about on Tuesdays at the lunchtime hour?
This problem is called Time Sent Optimization (TSO). Why is it so important?
Because it allows marketers to send emails at the optimal time for each contact. Also, it helps marketers engage more effectively with contacts, gaining contacts' attention when they are historically most attentive to their emails. Moreover, suppose that you want to start an advertising campaign. The more emails will be opened, the more the company will gain in terms of money and it will be easier for them to advertise some product. Not only, we do not want just to increase the open ratio, we also make sure that the user reads it. This translates is clicking the email, like scrolling it or clicking on links present in it.
Most of the medium and big companies already use Time Sent Optimization for the reasons explained before. However, they do not publish how they did that because of business reasons. If someone would publish a way of doing this, then everyone will copy it and then the purpose of doing this will be useless because it is likely that at a certain time, each user, will receive a lot of emails from several companies and this would lead ruin the benefit of TSO.
In this thesis, we take into account the case of a company called Diennea which gave us their data to improve their open and click ratio on the communications they send to their users. At the end, through online A/B test results, we show the effectiveness of our proposed approach and how to further improve it.
Tipologia del documento
Tesi di laurea
(Laurea magistrale)
Autore della tesi
Potrimba, Petru
Relatore della tesi
Correlatore della tesi
Scuola
Corso di studio
Ordinamento Cds
DM270
Parole chiave
Marketing,Sent Time Optimization,Machine Learning,CNN
Data di discussione della Tesi
8 Ottobre 2021
URI
Altri metadati
Tipologia del documento
Tesi di laurea
(NON SPECIFICATO)
Autore della tesi
Potrimba, Petru
Relatore della tesi
Correlatore della tesi
Scuola
Corso di studio
Ordinamento Cds
DM270
Parole chiave
Marketing,Sent Time Optimization,Machine Learning,CNN
Data di discussione della Tesi
8 Ottobre 2021
URI
Statistica sui download
Gestione del documento: