Big Data-Driven Marketing: How Machine Learning Outperforms Marketers’ Gut-Feeling
This paper shows how big data can be experimentally used at large scale for marketing purposes at a mobile network operator. We present results from a large-scale experiment in a MNO in Asia where we use machine learning to segment customers for text-based marketing. This leads to conversion rates f...
| Main Authors: | , , , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | en_US |
| Published: |
Springer-Verlag Berlin Heidelberg
2014
|
| Online Access: | http://hdl.handle.net/1721.1/92459 https://orcid.org/0000-0002-8053-9983 https://orcid.org/0000-0001-9086-589X |
| _version_ | 1811073663908184064 |
|---|---|
| author | Sundsøy, Pål Bjelland, Johannes Iqbal, Asif M. Pentland, Alex Paul de Montjoye, Yves-Alexandre |
| author2 | Massachusetts Institute of Technology. Media Laboratory |
| author_facet | Massachusetts Institute of Technology. Media Laboratory Sundsøy, Pål Bjelland, Johannes Iqbal, Asif M. Pentland, Alex Paul de Montjoye, Yves-Alexandre |
| author_sort | Sundsøy, Pål |
| collection | MIT |
| description | This paper shows how big data can be experimentally used at large scale for marketing purposes at a mobile network operator. We present results from a large-scale experiment in a MNO in Asia where we use machine learning to segment customers for text-based marketing. This leads to conversion rates far superior to the current best marketing practices within MNOs.
Using metadata and social network analysis, we created new metrics to identify customers that are the most likely to convert into mobile internet users. These metrics falls into three categories: discretionary income, timing, and social learning. Using historical data, a machine learning prediction model is then trained, validated, and used to select a treatment group. Experimental results with 250 000 customers show a 13 times better conversion-rate compared to the control group. The control group is selected using the current best practice marketing. The model also shows very good properties in the longer term, as 98% of the converted customers in the treatment group renew their mobile internet packages after the campaign, compared to 37% in the control group. These results show that data-driven marketing can significantly improve conversion rates over current best-practice marketing strategies. |
| first_indexed | 2024-09-23T09:36:36Z |
| format | Article |
| id | mit-1721.1/92459 |
| institution | Massachusetts Institute of Technology |
| language | en_US |
| last_indexed | 2024-09-23T09:36:36Z |
| publishDate | 2014 |
| publisher | Springer-Verlag Berlin Heidelberg |
| record_format | dspace |
| spelling | mit-1721.1/924592022-09-26T12:37:38Z Big Data-Driven Marketing: How Machine Learning Outperforms Marketers’ Gut-Feeling Sundsøy, Pål Bjelland, Johannes Iqbal, Asif M. Pentland, Alex Paul de Montjoye, Yves-Alexandre Massachusetts Institute of Technology. Media Laboratory Pentland, Alex Paul de Montjoye, Yves-Alexandre This paper shows how big data can be experimentally used at large scale for marketing purposes at a mobile network operator. We present results from a large-scale experiment in a MNO in Asia where we use machine learning to segment customers for text-based marketing. This leads to conversion rates far superior to the current best marketing practices within MNOs. Using metadata and social network analysis, we created new metrics to identify customers that are the most likely to convert into mobile internet users. These metrics falls into three categories: discretionary income, timing, and social learning. Using historical data, a machine learning prediction model is then trained, validated, and used to select a treatment group. Experimental results with 250 000 customers show a 13 times better conversion-rate compared to the control group. The control group is selected using the current best practice marketing. The model also shows very good properties in the longer term, as 98% of the converted customers in the treatment group renew their mobile internet packages after the campaign, compared to 37% in the control group. These results show that data-driven marketing can significantly improve conversion rates over current best-practice marketing strategies. United States. Army Research Office (Cooperative Agreement Number W911NF-09-2-0053) MIT Media Lab Consortium 2014-12-23T16:13:04Z 2014-12-23T16:13:04Z 2014 Article http://purl.org/eprint/type/ConferencePaper 978-3-319-05578-7 978-3-319-05579-4 0302-9743 1611-3349 http://hdl.handle.net/1721.1/92459 Sundsøy, Pål, Johannes Bjelland, Asif M. Iqbal, Alex “Sandy” Pentland, and Yves-Alexandre de Montjoye. “Big Data-Driven Marketing: How Machine Learning Outperforms Marketers’ Gut-Feeling.” Social Computing, Behavioral-Cultural Modeling and Prediction (2014): 367–374. https://orcid.org/0000-0002-8053-9983 https://orcid.org/0000-0001-9086-589X en_US http://dx.doi.org/10.1007/978-3-319-05579-4_45 Social Computing, Behavioral-Cultural Modeling and Prediction Creative Commons Attribution-Noncommercial-Share Alike http://creativecommons.org/licenses/by-nc-sa/4.0/ application/pdf Springer-Verlag Berlin Heidelberg MIT web domain |
| spellingShingle | Sundsøy, Pål Bjelland, Johannes Iqbal, Asif M. Pentland, Alex Paul de Montjoye, Yves-Alexandre Big Data-Driven Marketing: How Machine Learning Outperforms Marketers’ Gut-Feeling |
| title | Big Data-Driven Marketing: How Machine Learning Outperforms Marketers’ Gut-Feeling |
| title_full | Big Data-Driven Marketing: How Machine Learning Outperforms Marketers’ Gut-Feeling |
| title_fullStr | Big Data-Driven Marketing: How Machine Learning Outperforms Marketers’ Gut-Feeling |
| title_full_unstemmed | Big Data-Driven Marketing: How Machine Learning Outperforms Marketers’ Gut-Feeling |
| title_short | Big Data-Driven Marketing: How Machine Learning Outperforms Marketers’ Gut-Feeling |
| title_sort | big data driven marketing how machine learning outperforms marketers gut feeling |
| url | http://hdl.handle.net/1721.1/92459 https://orcid.org/0000-0002-8053-9983 https://orcid.org/0000-0001-9086-589X |
| work_keys_str_mv | AT sundsøypal bigdatadrivenmarketinghowmachinelearningoutperformsmarketersgutfeeling AT bjellandjohannes bigdatadrivenmarketinghowmachinelearningoutperformsmarketersgutfeeling AT iqbalasifm bigdatadrivenmarketinghowmachinelearningoutperformsmarketersgutfeeling AT pentlandalexpaul bigdatadrivenmarketinghowmachinelearningoutperformsmarketersgutfeeling AT demontjoyeyvesalexandre bigdatadrivenmarketinghowmachinelearningoutperformsmarketersgutfeeling |