Abstract

Although business intelligence is dependent on CRM, it still encounters issues such as bad data quality, weak governance structures and growing interest around data privacy. To solve these problems, this approach present a unified framework, the `Trustworthy Analytics Pipeline' (TAP). This structure combines the three most important pillars to give you data that is trustworthy enough to support your decision making. The TAP approach is realized by a number of steps: it starts using PhD at its ingestion layer for immediate tokenization and masking of data. Then, the processed data goes through an automated Data Quality (DQ) engine for checking quality & completeness and looking at lineage. Any exceptions raised in this process are remediated via human-in-the-loop stewardship. Evaluation of this approach on a synthetic dataset of 431 customer instances artificially contaminated with common data errors. The pipeline was implemented with Python for data processing, SQL database and BI platform for governance logs and the final analysis respectively. The results suggest that the approach is able to discover and repair data problems prior to analysis, maintains privacy while maximizing data utility, and provides full traceability of data lineage. Ultimately, this forward-looking model is aimed at fostering trust in CRM analytics so that companies can confidently use these job aides to craft important business decisions.

References

• A. Bleier, A. Goldfarb, and C. Tucker, “Consumer privacy and the future of data-based innovation and marketing,” Int. J. Res. Mark., vol. 37, no. 3, pp. 466–480, 2020.
• R. Dew, E. Ascarza, O. Netzer, and N. Sicherman, “Detecting routines: Applications to ridesharing customer relationship management,” J. Mark. Res., 2023.
• J.-P. Dubé and S. Misra, “Personalized pricing and consumer welfare,” J. Polit. Econ., vol. 131, no. 1, pp. 131–189, 2023.
• Y. Deng and C. F. Mela, “TV viewing and advertising targeting,” J. Mark. Res., vol. 55, no. 1, pp. 99–118, 2018.
• K. N. Lemon and P. C. Verhoef, “Understanding customer experience throughout the customer journey,” J. Mark., vol. 80, no. 6, pp. 69–96, 2016. https://doi.org/10.1509/jm.15.0420
• K. Mrkva, E. J. Johnson, S. Gächter, and A. Herrmann, “Moderating loss aversion: Loss aversion has moderators, but reports of its death are greatly exaggerated,” J. Consum. Psychol., vol. 30, no. 3, pp. 407–428, 2020.
• H. S. Nair, S. Misra, W. J. Hornbuckle IV, R. Mishra, and A. Acharya, “Big data and marketing analytics in gaming: Combining empirical models and field experimentation,” Mark. Sci., vol. 36, no. 5, pp. 699–725, 2017.
• S. Narayanan and P. Manchanda, “An empirical analysis of individual level casino gambling behavior,” Quant. Mark. Econ., vol. 10, pp. 27–62, 2012. https://doi.org/10.1007/s11129-011-9110-7
• N. Padilla, E. Ascarza, and O. Netzer, “The customer journey as a source of information,” SSRN 4612478, 2023.
• P. Rossi, R. McCulloch, and G. Allenby, “The value of purchase history data in target marketing,” Mark. Sci., vol. 15, no. 4, pp. 301–394, 1996.
• D. Zantedeschi, E. M. Feit, and E. T. Bradlow, “Measuring multichannel advertising response,” Manag. Sci., vol. 63, no. 8, pp. 2706–2728, 2017.
• T. H. Gui and T. H. Drerup, “Designing promises with reference-dependent customers: The case of online grocery delivery time,” SSRN 4298782, 2022.
• A. L. Brown, T. Imai, F. M. Vieider, and C. F. Camerer, “Meta-analysis of empirical estimates of loss aversion,” J. Econ. Lit., vol. 62, no. 2, pp. 485–516, 2024.