Machine Learning for Business Process Improvement
Expert-defined terms from the Professional Certificate in Business Process Management with Artificial Intelligence course at Greenwich School of Business and Finance. Free to read, free to share, paired with a professional course.
Active Learning #
Active learning is a subfield of machine learning that involves actively selecting the most informative data points for human annotation, rather than passively relying on a fixed dataset. This approach is particularly useful in business process improvement, where it can help to reduce the cost and time associated with data labeling. For example, in a customer service chatbot, active learning can be used to select the most uncertain or informative user inputs for human review and annotation.
Adversarial Attack #
An adversarial attack is a type of cyber attack that involves manipulating the input data to a machine learning model in order to cause it to make a misclassification or produce a incorrect output. In the context of business process improvement, adversarial attacks can be used to test the robustness of machine learning models and identify potential vulnerabilities. For example, in a fraud detection system, adversarial attacks can be used to simulate malicious activity and test the model's ability to detect it.
Agent #
Based Modeling: Agent-based modeling is a simulation technique that involves modeling complex systems as interactions between individual agents or entities. In business process improvement, agent-based modeling can be used to simulate the behavior of employees, customers, or other stakeholders, and identify opportunities for process improvement. For example, in a call center, agent-based modeling can be used to simulate the behavior of customers and agents, and identify strategies for reducing wait times and improving customer satisfaction.
Anomaly Detection #
Anomaly detection is a type of machine learning that involves identifying data points or patterns that are significantly different from the norm. In business process improvement, anomaly detection can be used to identify inefficiencies or problems in a process, such as errors or exceptions. For example, in a manufacturing process, anomaly detection can be used to identify defective products or unusual patterns of production.
Artificial General Intelligence #
Artificial general intelligence refers to a type of machine intelligence that is capable of performing any intellectual task that a human can. In business process improvement, artificial general intelligence has the potential to automate many tasks and improve decision-making. For example, in a financial institution, artificial general intelligence can be used to analyze financial data and make predictions about market trends.
Artificial Intelligence #
Artificial intelligence refers to the use of machine learning and other techniques to enable computers to perform intelligent tasks. In business process improvement, artificial intelligence can be used to automate tasks, improve decision-making, and enhance customer experience. For example, in a retail store, artificial intelligence can be used to analyze customer data and make personalized recommendations.
Association Rule Learning #
Association rule learning is a type of machine learning that involves identifying patterns and relationships between different variables. In business process improvement, association rule learning can be used to identify correlations between different process metrics, such as cycle time and cost. For example, in a supply chain, association rule learning can be used to identify patterns of demand and optimize inventory management.
Autonomous System #
An autonomous system is a type of machine learning system that is capable of operating independently without human intervention. In business process improvement, autonomous systems can be used to automate tasks and improve decision-making. For example, in a manufacturing process, an autonomous system can be used to control production and optimize quality.
Backpropagation #
Backpropagation is a training algorithm used in neural networks to minimize the error between predicted and actual outputs. In business process improvement, backpropagation can be used to train neural networks to predict process outcomes, such as cycle time or cost. For example, in a call center, backpropagation can be used to train a neural network to predict the likelihood of a customer churn.
Bayesian Network #
A Bayesian network is a type of probabilistic model that represents relationships between different variables. In business process improvement, Bayesian networks can be used to model complex systems and predict process outcomes. For example, in a financial institution, a Bayesian network can be used to model the probability of loan default and predict credit risk.
Business Process Management #
Business process management refers to the discipline of managing and improving business processes. In the context of machine learning, business process management involves using machine learning and other techniques to analyze and optimize business processes. For example, in a manufacturing company, business process management can be used to analyze production processes and identify opportunities for improvement.
Business Process Model #
A business process model is a representation of a business process, typically using a flowchart or other visual notation. In machine learning, business process models can be used to train machine learning models and predict process outcomes. For example, in a call center, a business process model can be used to train a machine learning model to predict the likelihood of a customer churn.
Case #
Based Reasoning: Case-based reasoning is a type of machine learning that involves solving new problems based on the similarity to previous cases. In business process improvement, case-based reasoning can be used to identify solutions to problems based on historical data. For example, in a customer service chatbot, case-based reasoning can be used to identify solutions to customer inquiries based on previous interactions.
Classification #
Classification is a type of machine learning that involves assigning a label or category to a new instance based on its features. In business process improvement, classification can be used to predict process outcomes, such as cycle time or cost. For example, in a credit risk assessment, classification can be used to predict the likelihood of loan default.
Clustering #
Clustering is a type of machine learning that involves grouping similar instances together based on their features. In business process improvement, clustering can be used to identify patterns and trends in process data. For example, in a customer segmentation analysis, clustering can be used to identify customer segments based on their behavior and demographics.
Cognitive Computing #
Cognitive computing refers to the use of machine learning and other techniques to mimic human cognition. In business process improvement, cognitive computing can be used to analyze and interpret complex data, such as text and images. For example, in a document analysis, cognitive computing can be used to extract relevant information and identify patterns.
Collaborative Filtering #
Collaborative filtering is a type of machine learning that involves recommending items based on the preferences of similar users. In business process improvement, collaborative filtering can be used to recommend process improvements based on the experiences of similar organizations. For example, in a supply chain, collaborative filtering can be used to recommend suppliers based on the experiences of similar companies.
Convolutional Neural Network #
A convolutional neural network is a type of neural network that is particularly well-suited to image and signal processing. In business process improvement, convolutional neural networks can be used to analyze and interpret complex data, such as images and videos. For example, in a quality control inspection, a convolutional neural network can be used to detect defects and identify patterns.
Data Mining #
Data mining refers to the process of discovering patterns and relationships in large datasets. In business process improvement, data mining can be used to identify trends and patterns in process data, such as cycle time and cost. For example, in a customer segmentation analysis, data mining can be used to identify customer segments based on their behavior and demographics.
Decision Tree #
A decision tree is a type of machine learning model that involves splitting data into subsets based on features. In business process improvement, decision trees can be used to predict process outcomes, such as cycle time or cost. For example, in a credit risk assessment, a decision tree can be used to predict the likelihood of loan default.
Deep Learning #
Deep learning refers to a type of machine learning that involves the use of neural networks with multiple layers. In business process improvement, deep learning can be used to analyze and interpret complex data, such as text and images. For example, in a document analysis, deep learning can be used to extract relevant information and identify patterns.
Dimensionality Reduction #
Dimensionality reduction refers to the process of reducing the number of features or dimensions in a dataset. In business process improvement, dimensionality reduction can be used to simplify complex datasets and improve the accuracy of machine learning models. For example, in a customer segmentation analysis, dimensionality reduction can be used to reduce the number of features and identify the most important factors.
Ensemble Method #
An ensemble method is a type of machine learning that involves combining the predictions of multiple models. In business process improvement, ensemble methods can be used to improve the accuracy of machine learning models and reduce the risk of overfitting. For example, in a credit risk assessment, an ensemble method can be used to combine the predictions of multiple models and improve the accuracy of the assessment.
Expert System #
An expert system is a type of machine learning model that involves mimicking the decision-making of a human expert. In business process improvement, expert systems can be used to analyze and interpret complex data, such as text and images. For example, in a document analysis, an expert system can be used to extract relevant information and identify patterns.
Feature Engineering #
Feature engineering refers to the process of selecting and transforming raw data into features that can be used in machine learning models. In business process improvement, feature engineering can be used to improve the accuracy of machine learning models and reduce the risk of overfitting. For example, in a customer segmentation analysis, feature engineering can be used to
Fuzzy Logic #
Fuzzy logic is a type of machine learning that involves representing uncertainty and imprecision in data. In business process improvement, fuzzy logic can be used to model complex systems and predict process outcomes. For example, in a quality control inspection, fuzzy logic can be used to model the uncertainty of inspection results and predict the likelihood of defects.
Genetic Algorithm #
A genetic algorithm is a type of machine learning that involves searching for optimal solutions using evolutionary principles. In business process improvement, genetic algorithms can be used to optimize process parameters, such as cycle time and cost. For example, in a supply chain, a genetic algorithm can be used to optimize inventory management and reduce costs.
Gradient Boosting #
Gradient boosting is a type of machine learning that involves combining multiple weak models to create a strong predictive model. In business process improvement, gradient boosting can be used to predict process outcomes, such as cycle time or cost. For example, in a credit risk assessment, gradient boosting can be used to predict the likelihood of loan default.
Graph #
Based Method: A graph-based method is a type of machine learning that involves representing data as a graph or network. In business process improvement, graph-based methods can be used to model complex systems and predict process outcomes. For example, in a social network analysis, a graph-based method can be used to model the relationships between employees and predict the likelihood of information diffusion.
Instance #
Based Learning: Instance-based learning is a type of machine learning that involves solving new problems based on the similarity to previous instances. In business process improvement, instance-based learning can be used to identify solutions to problems based on historical data. For example, in a customer service chatbot, instance-based learning can be used to identify solutions to customer inquiries based on previous interactions.
K-Means Clustering: K-Means clustering is a type of machine learning that… #
In business process improvement, k-means clustering can be used to identify patterns and trends in process data. For example, in a customer segmentation analysis, k-means clustering can be used to identify customer segments based on their behavior and demographics.
K-Nearest Neighbors: K-Nearest neighbors is a type of machine learning th… #
In business process improvement, k-nearest neighbors can be used to predict process outcomes, such as cycle time or cost. For example, in a credit risk assessment, k-nearest neighbors can be used to predict the likelihood of loan default.
Machine Learning #
Machine learning refers to the use of algorithms and statistical models to enable computers to perform intelligent tasks. In business process improvement, machine learning can be used to analyze and interpret complex data, such as text and images. For example, in a document analysis, machine learning can be used to extract relevant information and identify patterns.
Natural Language Processing #
Natural language processing refers to the use of machine learning and other techniques to analyze and interpret human language. In business process improvement, natural language processing can be used to analyze and interpret text data, such as customer feedback and complaints. For example, in a customer service chatbot, natural language processing can be used to analyze and interpret customer inquiries and identify solutions.
Neural Network #
A neural network is a type of machine learning model that involves mimicking the structure and function of the human brain. In business process improvement, neural networks can be used to analyze and interpret complex data, such as images and signals. For example, in a quality control inspection, a neural network can be used to detect defects and identify patterns.
Optimization #
Optimization refers to the process of finding the best solution to a problem. In business process improvement, optimization can be used to improve process outcomes, such as cycle time and cost. For example, in a supply chain, optimization can be used to optimize inventory management and reduce costs.
Predictive Analytics #
Predictive analytics refers to the use of machine learning and other techniques to predict future outcomes. In business process improvement, predictive analytics can be used to predict process outcomes, such as cycle time or cost. For example, in a credit risk assessment, predictive analytics can be used to predict the likelihood of loan default.
Process Mining #
Process mining refers to the use of machine learning and other techniques to discover and analyze business processes. In business process improvement, process mining can be used to identify inefficiencies and problems in a process. For example, in a manufacturing process, process mining can be used to identify bottlenecks and optimize production.
Random Forest #
A random forest is a type of machine learning model that involves combining the predictions of multiple decision trees. In business process improvement, random forests can be used to predict process outcomes, such as cycle time or cost. For example, in a credit risk assessment, a random forest can be used to predict the likelihood of loan default.
Regression #
Regression is a type of machine learning that involves predicting a continuous output variable. In business process improvement, regression can be used to predict process outcomes, such as cycle time or cost. For example, in a supply chain, regression can be used to predict the demand for a product and optimize inventory management.
Reinforcement Learning #
Reinforcement learning is a type of machine learning that involves learning from feedback and trial and error. In business process improvement, reinforcement learning can be used to optimize process outcomes, such as cycle time and cost. For example, in a manufacturing process, reinforcement learning can be used to optimize production and reduce costs.
Rule #
Based System: A rule-based system is a type of machine learning model that involves representing knowledge as a set of rules. In business process improvement, rule-based systems can be used to model complex systems and predict process outcomes. For example, in a quality control inspection, a rule-based system can be used to model the rules for inspection and predict the likelihood of defects.
Self #
Organizing Map: A self-organizing map is a type of machine learning model that involves representing high-dimensional data as a low-dimensional map. In business process improvement, self-organizing maps can be used to identify patterns and trends in process data. For example, in a customer segmentation analysis, a self-organizing map can be used to identify customer segments based on their behavior and demographics.
Sentiment Analysis #
Sentiment analysis is a type of machine learning that involves analyzing and interpreting human emotions and opinions. In business process improvement, sentiment analysis can be used to analyze and interpret customer feedback and complaints. For example, in a customer service chatbot, sentiment analysis can be used to analyze and interpret customer inquiries and identify solutions.
Simulation #
Simulation refers to the use of machine learning and other techniques to model and analyze complex systems. In business process improvement, simulation can be used to model and analyze business processes, such as supply chains and manufacturing processes. For example, in a manufacturing process, simulation can be used to model and optimize production and reduce costs.
Support Vector Machine #
A support vector machine is a type of machine learning model that involves finding the best hyperplane to separate classes. In business process improvement, support vector machines can be used to predict process outcomes, such as cycle time or cost. For example, in a credit risk assessment, a support vector machine can be used to predict the likelihood of loan default.
Swarm Intelligence #
Swarm intelligence refers to the use of machine learning and other techniques to model and analyze complex systems, such as swarms of agents. In business process improvement, swarm intelligence can be used to model and analyze complex systems, such as supply chains and manufacturing processes. For example, in a manufacturing process, swarm intelligence can be used to model and optimize production and reduce costs.
Text Mining #
Text mining refers to the use of machine learning and other techniques to extract and analyze text data. In business process improvement, text mining can be used to analyze and interpret text data, such as customer feedback and complaints. For example, in a customer service chatbot, text mining can be used to analyze and interpret customer inquiries and identify solutions.
Time Series Analysis #
Time series analysis refers to the use of machine learning and other techniques to analyze and forecast time series data. In business process improvement, time series analysis can be used to predict process outcomes, such as cycle time or cost. For example, in a supply chain, time series analysis can be used to predict demand and optimize inventory management.
Transfer Learning #
Transfer learning refers to the use of machine learning models trained on one task to improve performance on another task. In business process improvement, transfer learning can be used to improve the accuracy of machine learning models and reduce the need for training data. For example, in a credit risk assessment, transfer learning can be used to improve the accuracy of the assessment by using models trained on other tasks, such as fraud detection.
Unsupervised Learning #
Unsupervised learning refers to the use of machine learning algorithms to discover patterns and relationships in data without labels or supervision. In business process improvement, unsupervised learning can be used to identify patterns and trends in process data, such as customer behavior and demographics. For example, in a customer segmentation analysis, unsupervised learning can be used to identify customer segments based on their behavior and demographics.
Value Chain Analysis #
Value chain analysis refers to the use of machine learning and other techniques to analyze and optimize the value chain of a business. In business process improvement, value chain analysis can be used to identify inefficiencies and problems in the value chain and optimize business processes. For example, in a manufacturing company, value chain analysis can be used to identify bottlenecks and optimize production.
Virtual Reality #
Virtual reality refers to the use of machine learning and other techniques to create and simulate virtual environments. In business process improvement, virtual reality can be used to simulate and analyze business processes, such as supply chains and manufacturing processes. For example, in a manufacturing process, virtual reality can be used to simulate and optimize production and reduce costs.