本論文探討機器學習（Machine Learning, ML）技術在高科技行業企業對企業（B2B）潛在客戶開發中的有效性。
為此，本研究以IC設計公司eMemory Technology為案例，演示一種結合 ML和高科技和營銷領域經驗豐富的專
業人士以及eMemory經理問卷調查的混合方法的有效性。本研究的主要範圍是識別B2B客戶分類和目標的最重要因
素，旨在提高eMemory的B2B銷售效率。為實現這一目標，本研究比較從監督和非監督ML方法得出的特徵重要性結
果與從問卷調查中得出的相關性。結果顯示，B2B客戶分類和目標最關鍵的因素是 “產業”、“市值”、“員工人數” 以
及 “關係”。本研究還強調混合方法的有效性和ML技術在解決B2B銷售研究缺口方面的潛力，為尋求利用ML進行客戶
定位的高科技公司提供實用洞見。此研究的結果對學術理論和實際應用都具有重要意義。從理論上講，本研究通過使
用ML解決B2B銷售研究缺口，為當前文獻做出貢獻。它提供一些新的見解，探討如何應用ML技術來識別B2B銷售的潛
在客戶，尤其是在高科技行業中。從實用角度來看，本研究為尋求利用ML進行客戶定位的高科技公司提供有價值的洞
見。

This thesis explores the effectiveness of machine learning (ML) techniques in prospecting
potential customers for the high-tech industry business-to-business (B2B). To this end, the
study focuses on the case of eMemory Technology, an IC design house, to demonstrate the
effectiveness of a hybrid approach that combines ML and a questionnaire survey from experienced
professionals in high-tech and marketing, as well as eMemory’s managers. The main
scope of this study is to identify the most crucial factors for B2B customer segmentation and
targeting, with the ultimate goal of improving eMemory’s B2B sales effectiveness. To achieve
this scope, the study compares the feature importance results obtained from supervised and
unsupervised ML methods with the correlations derived from the survey. The findings indicate
that the most critical factors for B2B customer segmentation and targeting are ”industry”,
”market capitalization”, ”number of employees”, and ”relationship”. The study also highlights
the effectiveness of the hybrid approach and the potential of ML techniques in addressing B2B
sales research gaps, providing practical insights for high-tech companies seeking to leverage ML
for customer targeting. The results of this research have significant implications for both academic
theory and practical applications. Theoretically, this study contributes to the current
literature by addressing research gaps in B2B sales using ML. It provides new insights into
applying ML techniques in identifying potential customers for B2B sales, particularly in the
high-tech industry. From a practical standpoint, this study offers valuable insights for high-tech
companies seeking to leverage ML for customer targeting.

Abstract (Chinese) I
Acknowledgements II
Abstract III
Contents IV
List of Figures VI
List of Tables VII
1 Introduction 1
2 Literature Review 4
2.1 B2B Customer Prospecting Methods . . . . . . . . . . . . . . . . . . . . . . . . 4
2.2 Using ML for Identifying B2B Customers and Research Gaps . . . . . . . . . . . 5
3 Data Collection and Processing 7
3.1 ML Dataset Collection and Sources . . . . . . . . . . . . . . . . . . . . . . . . . 7
3.2 ML Data Pre-processing and Feature Engineering . . . . . . . . . . . . . . . . . 8
3.3 Questionnaire Survey Design and Sampling . . . . . . . . . . . . . . . . . . . . . 9
4 Research Methodology 11
4.1 Research Design and Approach . . . . . . . . . . . . . . . . . . . . . . . . . . . 11
IV
4.2 ML Algorithms Selection and Implementation . . . . . . . . . . . . . . . . . . . 12
4.2.1 Supervised Machine Learning . . . . . . . . . . . . . . . . . . . . . . . . 12
4.2.2 Unsupervised Machine Learning . . . . . . . . . . . . . . . . . . . . . . . 15
4.2.3 Performance Evaluation Metrics . . . . . . . . . . . . . . . . . . . . . . . 17
4.2.4 Data Analysis Methods . . . . . . . . . . . . . . . . . . . . . . . . . . . . 20
5 Results and Discussion 22
5.1 Descriptive Statistics of Datasets and Survey . . . . . . . . . . . . . . . . . . . . 22
5.1.1 Descriptive Statistics of ML Datasets . . . . . . . . . . . . . . . . . . . . 22
5.1.2 Descriptive Statistics of Survey Data . . . . . . . . . . . . . . . . . . . . 23
5.2 Performance Evaluation of ML Models . . . . . . . . . . . . . . . . . . . . . . . 24
5.3 Correlation Matrix from Survey Results . . . . . . . . . . . . . . . . . . . . . . . 25
5.4 Feature Importance Analysis and Comparison . . . . . . . . . . . . . . . . . . . 26
5.4.1 Feature Importance for Supervised Models . . . . . . . . . . . . . . . . . 26
5.5 Feature Importance Analysis for Unsupervised Models . . . . . . . . . . . . . . 27
5.5.1 Feature Importance Analysis for Survey Results . . . . . . . . . . . . . . 28
5.6 Discussion of Findings and Implications . . . . . . . . . . . . . . . . . . . . . . . 30
6 Conclusion and Future Work 32
6.1 Summary of Research Findings . . . . . . . . . . . . . . . . . . . . . . . . . . . 32
6.2 Contributions to Theory and Practice . . . . . . . . . . . . . . . . . . . . . . . . 33
6.3 Limitations and Directions for Future Research . . . . . . . . . . . . . . . . . . 34
List of Figures 38
List of Tables 44

1. Anand, A. et al. (2010). “An approach for classification of highly imbalanced data using weighting and under sampling”. In: Amino acids 39, pp. 1385–1391.
2. Becker, J. U., G. Greve, and S. Albers (2009). “The impact of technological and organizational implementation of CRM on customer acquisition”. In: maintenance, and retention. International Journal of Research in Marketing 26.3, pp. 207–215.
3. Choi, J., D. R. Bell, and L. M. Lodish (2010). Traditional and IS-enabled Customer Acquisition for an Internet Retailer: Why New Buyer Acquisition Varies over Geographies and by Method. Knowledge@ Wharton.
4. Goi, C. L. (2009). “A review of marketing mix: 4Ps or more”. In: International journal of marketing studies 1, pp. 2–15.
5. Liu, C. et al. (2015). “Financial fraud detection model: Based on random forest”. In: International Journal of Economics and Finance 7.7.
Min, S. et al. (2016). “Customer acquisition and retention spending: An analytical model and empirical investigation in wireless telecommunications markets”. In: Journal of Marketing
Research 53.5, pp. 728–744.
6. Moradi, M. and M. Dass (2022). “Applications of artificial intelligence in B2B marketing: Challenges and future directions”. In: Industrial Marketing Management 107, pp. 300–314.
7. Morgan, R. M. and S. D. Hunt (1994). “The commitment-trust theory of relationship marketing”. In: Journal of Marketing 58.3, pp. 20–38.
Mortensen, S. et al. (2019). In 2019 Systems and Information Engineering Design Symposium (SIEDS). s, pp. 1–5.
8. Norlin, P. and V. Paulsrud (2017). Identifying New Customers Using Machine Learning: A case study on B2B-sales in the Swedish IT-consulting sector. url: http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-210256.
9. Palmatier, R. W. et al. (2006). “Factors influencing the effectiveness of relationship marketing: A meta-analysis”. In: Journal of Marketing 70.4, pp. 136–153. Paschen, J., M. Wilson, and J. J. Ferreira (2020). "Collaborative Intelligence: How human and artificial intelligence create value along the B2B sales funnel”. In: Business Horizons 63.3, pp. 403–414.
10. Raizada, S. and J. R. Saini (2021). “Comparative Analysis of Supervised Machine Learning Techniques for Sales Forecasting”. In: International Journal of Advanced Computer Science and Applications 12.11.
11. Tama, B. A. and K. H. Rhee (2019). “An in-depth experimental study of anomaly detection using gradient boosted machine”. In: Neural Computing and Applications 31, pp. 955–965.
12. Vujovi´c, ˇZ. (2021). “Classification model evaluation metrics”. In: International Journal of Advanced Computer Science and Applications 12.6, pp. 599–606.
13. Wisesa, O., A. Adriansyah, and O. I. Khalaf (2020). “Prediction analysis for business to business (B2B) sales of telecommunication services using machine learning techniques”. In: Majlesi Journal of Electrical Engineering 14.4, pp. 145–153.
14. Wu, J. and Z. Lin (Aug. 2005). “Research on customer segmentation model by clustering”. In: Proceedings of the 7th international conference on Electronic commerce. ACM, pp. 316–318.