Forecasting Nike’s Sales using Facebook Data

Linda Camilla Boldt, Vinothan Vinayagamoorthy, Florian Winder, Schnittger Melanie, Mats Ekram, Raghava Rao Mukkamala, Niels Buus Lassen, Benjamin Flesch, Abid Hussain, Ravi Vatrapu

    Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review

    Abstract

    This paper tests whether accurate sales forecasts for Nike are possible from Facebook data and how events related to Nike affect the activity on Nike’s Facebook pages. The paper draws from the AIDA sales framework (Awareness, Interest, Desire,and Action) from the domain of marketing and employs the method of social set analysis from the domain of computational social science to model sales from Big Social Data. The dataset consists of (a) selection of Nike’s Facebook pages with the number of likes, comments, posts etc. that have been registered for each page per day and (b) business data in terms of quarterly global sales figures published in Nike’s financial reports. An event study is also conducted using the Social Set Visualizer (SoSeVi). The findings suggest that Facebook data does have informational value. Some of the simple regression models have a high forecasting accuracy. The multiple regressions have a lower forecasting accuracy and cause analysis barriers due to data set characteristics such as perfect multicollinearity. The event study found abnormal activity around several Nike specific events but inferences about those activity spikes, whether they are purely event-related or coincidences, can only be determined after detailed case-bycase text analysis. Our findings help assess the informational value of Big Social Data for a company’s marketing strategy, sales operations and supply chain.
    This paper tests whether accurate sales forecasts for Nike are possible from Facebook data and how events related to Nike affect the activity on Nike’s Facebook pages. The paper draws from the AIDA sales framework (Awareness, Interest, Desire,and Action) from the domain of marketing and employs the method of social set analysis from the domain of computational social science to model sales from Big Social Data. The dataset consists of (a) selection of Nike’s Facebook pages with the number of likes, comments, posts etc. that have been registered for each page per day and (b) business data in terms of quarterly global sales figures published in Nike’s financial reports. An event study is also conducted using the Social Set Visualizer (SoSeVi). The findings suggest that Facebook data does have informational value. Some of the simple regression models have a high forecasting accuracy. The multiple regressions have a lower forecasting accuracy and cause analysis barriers due to data set characteristics such as perfect multicollinearity. The event study found abnormal activity around several Nike specific events but inferences about those activity spikes, whether they are purely event-related or coincidences, can only be determined after detailed case-bycase text analysis. Our findings help assess the informational value of Big Social Data for a company’s marketing strategy, sales operations and supply chain.
    LanguageEnglish
    Title of host publicationProceedings of the 2016 IEEE International Conference on Big Data (BigData '16)
    EditorsJames Joshi, George Karypis, Ling Liu
    Place of PublicationPiscataway, NJ
    PublisherIEEE
    Date2016
    Pages2447-2456
    ISBN (Print)9781467390057
    StatePublished - 2016
    Event2016 IEEE International Conference on Big Data - Washington, DC, United States
    Duration: 5 Dec 20168 Dec 2016
    http://cci.drexel.edu/bigdata/bigdata2016/

    Conference

    Conference2016 IEEE International Conference on Big Data
    CountryUnited States
    CityWashington, DC
    Period05/12/201608/12/2016
    Internet address

    Keywords

    • Predictive analytics
    • Big data analytics
    • Big social data
    • Event study
    • Nike
    • Facebook data analytics

    Cite this

    Boldt, L. C., Vinayagamoorthy, V., Winder, F., Melanie, S., Ekram, M., Mukkamala, R. R., ... Vatrapu, R. (2016). Forecasting Nike’s Sales using Facebook Data. In J. Joshi, G. Karypis, & L. Liu (Eds.), Proceedings of the 2016 IEEE International Conference on Big Data (BigData '16) (pp. 2447-2456). Piscataway, NJ: IEEE.
    Boldt, Linda Camilla ; Vinayagamoorthy, Vinothan ; Winder, Florian ; Melanie, Schnittger ; Ekram, Mats ; Mukkamala, Raghava Rao ; Buus Lassen, Niels ; Flesch, Benjamin ; Hussain, Abid ; Vatrapu, Ravi. / Forecasting Nike’s Sales using Facebook Data. Proceedings of the 2016 IEEE International Conference on Big Data (BigData '16). editor / James Joshi ; George Karypis ; Ling Liu. Piscataway, NJ : IEEE, 2016. pp. 2447-2456
    @inproceedings{655b5747f8fe410ca39b5ffe0194f3c8,
    title = "Forecasting Nike’s Sales using Facebook Data",
    abstract = "This paper tests whether accurate sales forecasts for Nike are possible from Facebook data and how events related to Nike affect the activity on Nike’s Facebook pages. The paper draws from the AIDA sales framework (Awareness, Interest, Desire,and Action) from the domain of marketing and employs the method of social set analysis from the domain of computational social science to model sales from Big Social Data. The dataset consists of (a) selection of Nike’s Facebook pages with the number of likes, comments, posts etc. that have been registered for each page per day and (b) business data in terms of quarterly global sales figures published in Nike’s financial reports. An event study is also conducted using the Social Set Visualizer (SoSeVi). The findings suggest that Facebook data does have informational value. Some of the simple regression models have a high forecasting accuracy. The multiple regressions have a lower forecasting accuracy and cause analysis barriers due to data set characteristics such as perfect multicollinearity. The event study found abnormal activity around several Nike specific events but inferences about those activity spikes, whether they are purely event-related or coincidences, can only be determined after detailed case-bycase text analysis. Our findings help assess the informational value of Big Social Data for a company’s marketing strategy, sales operations and supply chain.",
    keywords = "Predictive analytics, Big data analytics, Big social data, Event study, Nike, Facebook data analytics, Predictive analytics, Big data analytics, Big social data, Event study, Nike, Facebook data analytics",
    author = "Boldt, {Linda Camilla} and Vinothan Vinayagamoorthy and Florian Winder and Schnittger Melanie and Mats Ekram and Mukkamala, {Raghava Rao} and {Buus Lassen}, Niels and Benjamin Flesch and Abid Hussain and Ravi Vatrapu",
    year = "2016",
    language = "English",
    isbn = "9781467390057",
    pages = "2447--2456",
    editor = "James Joshi and George Karypis and Ling Liu",
    booktitle = "Proceedings of the 2016 IEEE International Conference on Big Data (BigData '16)",
    publisher = "IEEE",
    address = "United States",

    }

    Boldt, LC, Vinayagamoorthy, V, Winder, F, Melanie, S, Ekram, M, Mukkamala, RR, Buus Lassen, N, Flesch, B, Hussain, A & Vatrapu, R 2016, Forecasting Nike’s Sales using Facebook Data. in J Joshi, G Karypis & L Liu (eds), Proceedings of the 2016 IEEE International Conference on Big Data (BigData '16). IEEE, Piscataway, NJ, pp. 2447-2456, Washington, DC, United States, 05/12/2016.

    Forecasting Nike’s Sales using Facebook Data. / Boldt, Linda Camilla; Vinayagamoorthy, Vinothan; Winder, Florian; Melanie, Schnittger; Ekram, Mats; Mukkamala, Raghava Rao; Buus Lassen, Niels; Flesch, Benjamin; Hussain, Abid; Vatrapu, Ravi.

    Proceedings of the 2016 IEEE International Conference on Big Data (BigData '16). ed. / James Joshi; George Karypis; Ling Liu. Piscataway, NJ : IEEE, 2016. p. 2447-2456.

    Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review

    TY - GEN

    T1 - Forecasting Nike’s Sales using Facebook Data

    AU - Boldt,Linda Camilla

    AU - Vinayagamoorthy,Vinothan

    AU - Winder,Florian

    AU - Melanie,Schnittger

    AU - Ekram,Mats

    AU - Mukkamala,Raghava Rao

    AU - Buus Lassen,Niels

    AU - Flesch,Benjamin

    AU - Hussain,Abid

    AU - Vatrapu,Ravi

    PY - 2016

    Y1 - 2016

    N2 - This paper tests whether accurate sales forecasts for Nike are possible from Facebook data and how events related to Nike affect the activity on Nike’s Facebook pages. The paper draws from the AIDA sales framework (Awareness, Interest, Desire,and Action) from the domain of marketing and employs the method of social set analysis from the domain of computational social science to model sales from Big Social Data. The dataset consists of (a) selection of Nike’s Facebook pages with the number of likes, comments, posts etc. that have been registered for each page per day and (b) business data in terms of quarterly global sales figures published in Nike’s financial reports. An event study is also conducted using the Social Set Visualizer (SoSeVi). The findings suggest that Facebook data does have informational value. Some of the simple regression models have a high forecasting accuracy. The multiple regressions have a lower forecasting accuracy and cause analysis barriers due to data set characteristics such as perfect multicollinearity. The event study found abnormal activity around several Nike specific events but inferences about those activity spikes, whether they are purely event-related or coincidences, can only be determined after detailed case-bycase text analysis. Our findings help assess the informational value of Big Social Data for a company’s marketing strategy, sales operations and supply chain.

    AB - This paper tests whether accurate sales forecasts for Nike are possible from Facebook data and how events related to Nike affect the activity on Nike’s Facebook pages. The paper draws from the AIDA sales framework (Awareness, Interest, Desire,and Action) from the domain of marketing and employs the method of social set analysis from the domain of computational social science to model sales from Big Social Data. The dataset consists of (a) selection of Nike’s Facebook pages with the number of likes, comments, posts etc. that have been registered for each page per day and (b) business data in terms of quarterly global sales figures published in Nike’s financial reports. An event study is also conducted using the Social Set Visualizer (SoSeVi). The findings suggest that Facebook data does have informational value. Some of the simple regression models have a high forecasting accuracy. The multiple regressions have a lower forecasting accuracy and cause analysis barriers due to data set characteristics such as perfect multicollinearity. The event study found abnormal activity around several Nike specific events but inferences about those activity spikes, whether they are purely event-related or coincidences, can only be determined after detailed case-bycase text analysis. Our findings help assess the informational value of Big Social Data for a company’s marketing strategy, sales operations and supply chain.

    KW - Predictive analytics

    KW - Big data analytics

    KW - Big social data

    KW - Event study

    KW - Nike

    KW - Facebook data analytics

    KW - Predictive analytics

    KW - Big data analytics

    KW - Big social data

    KW - Event study

    KW - Nike

    KW - Facebook data analytics

    M3 - Article in proceedings

    SN - 9781467390057

    SP - 2447

    EP - 2456

    BT - Proceedings of the 2016 IEEE International Conference on Big Data (BigData '16)

    PB - IEEE

    CY - Piscataway, NJ

    ER -

    Boldt LC, Vinayagamoorthy V, Winder F, Melanie S, Ekram M, Mukkamala RR et al. Forecasting Nike’s Sales using Facebook Data. In Joshi J, Karypis G, Liu L, editors, Proceedings of the 2016 IEEE International Conference on Big Data (BigData '16). Piscataway, NJ: IEEE. 2016. p. 2447-2456.