The Essential Data Science
An Introductory Journal, with a Case Study on Agriculture.
Over the years the term Data Science has moved beyond an academic and big business environment, to what constitutes a fundamental part of our daily activities. From personalized advertisements on social media, to recommendation systems etc.
In this article, I hope to break down this term into little bits, and expose its friendly and necessary nature.
So, what is Data Science?
Data science is a field that deals with large volumes of data, using cutting-edge tools and techniques to identify trends and extract meaningful insights (Analytics), to inform decision making processes.
From an academic outlook it is a blend of Mathematics, Statistics and Computer Science to provide insights to make the best possible decisions, given the data available.
There are four major types of Analytics;
Descriptive Analytics: This is the process of using historic data to identify trends and relationships, that explains what has happened in an organization. It can be used to develop business strategy, financial statement analysis, develop key performance indicators and track performance.
Prescriptive Analytics: This is the process of using data to determine an optimal course of action. It answers the question “What should be done?”, or “What can we do to make _______ happen”. An Example is “ Recommender Systems”, where past data is used to suggest products you may like, and “Inventory Management Systems”, where statistic such as “Confidence Intervals” is used to suggest the optimal number of a product to buy, in order to reduce dead stock and increase sales.
Predictive Analytics: This is a form of advanced analytics that uses statistical modelling, data mining techniques, and machine learning to make predictions about the future, based on current and historic data. It answers the question “What could happen?”. Example predicting stock prices, credit risk modelling, customer churn prediction etc.
Diagnostic Analytics: This type of analytics explains why a trend or relationship occurred. It answers the question “Why did this happen?”. An example is Customer Analytics which segments customers and explains why each customer belongs to a particular group, also explains why retention rate is high or low. Another example can be seen in Macroeconomic Diagnostics, which explains the economic situation of a country, measures and assesses the source of inflation, measures the effect of monetary and fiscal policies etc.
Why is Data Science Important?
Apart from the reasons listed above, with the right analytical skills the world might just be “you” away from the next billion-dollar start-up, or 8-weeks long developed vaccine.
Get Ovbude Ehi’s stories in your inbox
Join Medium for free to get updates from this writer.
Let’s take the Agricultural sector as a case study:
Consumer demand has never been more sensitive, as we witness the transition of “Fast Food” businesses into a “Food Fast” era, where consumer preferences are leading to rising demand for healthy, fresh, and nutritious food options that can be made fast, and a healthy environment where their food has been produced, processed, and stored before it reaches their table.
With Data Science, problems like infectious crop diseases can be addressed with data from IoT-enabled solutions, that uses real-time monitoring of farms to detect potential problems and help farmers deploy corrective measures on time.
Additionally, to satisfy consumer demand, real-time data and past data can be used to form meaningful insights on customer behaviour, consumer behaviour, market segmentation and cropping patterns, which helps increase sales.
Another example is in Agricultural Financing. In this booming period of private equity and venture capital, investment bankers use past data and satellite imagery data to derive insights on crop performance, cultivation trends and weather patterns, to predict farm-level yields and hedge seasonality by investing in different products.
Considering Breaking into the field?
If it sounds interesting, below are a few tips from my experience on how you can get started:
1. Learn a programming language (Example; Python or R)
2. Open a Kaggle Account, this is an online community of data scientists and machine learning practitioners powered by Google.
3. Take the free Kaggle courses, this exposes you to what is possible with data science.
4. Get additional resources, like tutorials on YouTube, and Data Science Bootcamps that includes Statistics, Probability and Mathematics for data science, from websites like Udacity, Udemy and Datacamp for depth.
5. Focus on a project-based learning approach, this gives you the experience recruiters expects you to have, as you surf the web on how to solve the challenges you encounter while building analytical solutions.
6. Learn a data visualization software (e.g. Tableau or Power B.I): This is the easiest mode of communicating value with data, by representing data into visual/graphical format, highlighting the trends and outliers, and telling stories with dashboards.
Conclusion
As data becomes the most valuable commodity in the world, data science will add value to any business or organization who can analyze their data correctly.
A thorough understanding of its potential opens up dialogue for a more ethical line of argument on the limits to this kind of technology.
