Explaining machine learning models in sales predictions

@article{Bohanec2017ExplainingML,
  title={Explaining machine learning models in sales predictions},
  author={Marko Bohanec and Mirjana Kljajic Borstnar and M. Robnik-Sikonja},
  journal={Expert Syst. Appl.},
  year={2017},
  volume={71},
  pages={416-428}
}

Figures and Tables from this paper

Decision-making framework with double-loop learning through interpretable black-box machine learning models
TLDR
To the authors’ knowledge, this is the first attempt to support organizational learning with a framework combining ML explanations, ADR, and data mining methodology based on the CRISP-DM industry standard.
A decision support system for B2B CRM Systems using belief rules
TLDR
This work presents a methodology to create a Decision Support System (DSS) for Business to Business (B2B) sales that generates recommendations for actions to follow and actions to avoid to increase the chances of successfully closing a deal.
Organizational Learning Supported by Machine Learning Models Coupled with General Explanation Methods: A Case of B2B Sales Forecasting
TLDR
When the users embrace the proposed ML model and its explanations, they change their initial beliefs, make more accurate B2B sales predictions and detect other features of the process, not included in the ML model.
Explanation of Prediction Models with ExplainPrediction
TLDR
An overview of perturbation based approaches, and focus on a recently introduced implementation of two successful methods developed in Slovenia, EXPLAIN and IME, which can explain predictions of otherwise opaque models.
Interpretable machine learning for demand modeling with high-dimensional data using Gradient Boosting Machines and Shapley values
TLDR
This work proposes a conceptual model for sales modeling based on standard POS data available to any retailer and generates almost 500 potentially useful predictors of a focal SKU’s sales accordingly, and demonstrates how helpful it can be for marketing managers to decompose predictions into the effects of individual regressors by using an approximation of Shapley values for feature attribution.
Predicting and Defining B2B Sales Success with Machine Learning
TLDR
The research team generated several models to predict win propensities for individual sales opportunities, choosing the model with the greatest predictive power and ability to generate insights to use as the backbone for a client tool.
Business Analytics for Sales Pipeline Management in the Software Industry: A Machine Learning Perspective
TLDR
An artifact consisting of three models to map the end-to-end sales pipeline process using real business data from the company’s CRM system shows a superiority of the CatBoost and Random Forest algorithm over other supervised classifiers as the baseline.
On the current state of combining human and artificial intelligence for strategic organizational decision making
TLDR
An overview of the possibilities that current research identifies for integrating AI into organizational decision making under uncertainty is provided, summarized in a conceptual model that first explains how humans can use AI for decisionMaking under uncertainty and then identifies the challenges, pre-conditions, and consequences that must be considered.
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 58 REFERENCES
On Machine Learning towards Predictive Sales Pipeline Analytics
TLDR
A profile-specific two-dimensional Hawkes processes model is developed to capture the influence from seller's activities on their leads to the win outcome, coupled with lead's personalized profiles.
A Survey of the Application of Machine Learning in Decision Support Systems
TLDR
The content analysis of design-oriented research published between 1994 and 2013 suggests that the usefulness of machine learning for supporting decision-makers is dependent on the task, the phase of decision-making, and the applied technologies.
Visual Explanation of Evidence with Additive Classifiers
TLDR
A framework, ExplainD, is described for explaining decisions made by classifiers that use additive evidence, which applies to many widely used classifiers, including linear discriminants and many additive models.
Explaining Documents' Classifications
TLDR
The results show the explanations to be concise and document-specific, and to provide insight into the exact reasons for the classification decisions, into the workings of the classification models, and into the business application itself.
A Machine Learning Approach to Improving Dynamic Decision Making
TLDR
The proposed iterative approach is used to improve treatment strategies by predicting and eliminating treatment failures, i.e., insufficient or excessive treatment actions, based on information that is available in electronic medical record systems.
Integration of machine learning insights into organizational learning: A case of B2B sales forecasting
TLDR
Preliminary results of machine learning model performance are presented, with focus on distilled visualizations that create powerful, yet human comprehensible and actionable insights, enabling positive climate for reflection and contributing to continuous organizational learning.
Golden Rule of Forecasting : Be Conservative
This article proposes a unifying theory, or Golden Rule, of forecasting. The Golden Rule of Forecasting is to be conservative. A conservative forecast is consistent with cumulative knowledge about
Enhancing data stream predictions with reliability estimators and explanation
...
1
2
3
4
5
...