Applications of data science in marketing

Regardless of company size, the adoption of data science and machine learning for marketing has been rising in the industry. With this book, you will learn to implement data science techniques to understand the drivers behind the successes and failures of marketing campaigns.

Want to Learn

We have discussed the trends in marketing and how the trend has been toward more data-driven and quantitative marketing, often using data science and machine learning. There are various ways to apply data science and machine learning in the marketing industry and it will be beneficial for us to discuss the typical tasks and usage of data science and machine learning. In this section, we will cover the basics of machine learning, the different types of learning algorithms, and, typical data science workflow and process. Descriptive versus explanatory versus predictive analyses As we work through the exercises and projects in the upcoming chapters, there are mainly three different types of analyses that we are going to conduct throughout this book: descriptive, explanatory, and predictive analyses: Descriptive analysis: This is conducted to understand and describe the given dataset better. The purpose of this analysis is to quantitatively and statistically summarize the information that the data contains. For example, if you are conducting a descriptive analysis of user purchase history data, you will be answering such questions as What is the best selling item? What were the monthly sales like in the past year? What is the average price of the items that are sold? Throughout this book, we will be conducting descriptive analysis, whenever we introduce a new dataset. Especially, Key Performance Indicators and Visualizations, we will be discussing in more detail how to use descriptive analysis to analyze and compute key summary statistics, as well as visualizing the analysis results. Explanatory analysis: When the purpose of descriptive analysis is to answer the what and how from the data, explanatory analysis is to answer why using the data. This type of analysis is typically conducted when you have a specific question that you want to answer. As an example for e-commerce businesses, if you want to analyze what drives your users to make purchases, you would conduct explanatory analysis, not descriptive analysis. We will be discussing more detail about this type of analysis with examples in Chapter 3, Drivers behind Marketing Engagement; and Chapter 4, From Engagement to Conversion, where we are going to use explanatory analyses to answer such questions as What drives users to engage with our marketing campaigns more? and What makes users purchase items from our retail shop? Predictive analysis: This analysis is conducted when there is a specific future event that you would like to predict. The purpose of this analysis is to build machine learning models that learn from the historical data and make predictions about events that will happen in the future. Similar to the previous examples of e-commerce and purchase history data, one of the questions you can answer from this type of analysis may be, Which user is the most likely to purchase within the next seven days? Typically, to conduct predictive analysis, you will have to first run descriptive and explanatory analyses to have a better understanding of the data and generate ideas on what types of learning algorithms and approaches to use for the given project. visit

Top Tutorials For Applications of data science in marketing