Data Science and Everyday Life

A Brief Introduction to What is Data Science

In simple words, Data Science is a process of collecting data, storing data in usable form, cleaning data to remove unwanted entries, and finally using the clean data to gain insights and meaningful outcomes using Machine Learning Algorithms.

• The Data Lifecycle includes the following main processes:

• Define and understand the problem.

• Data Collection.

• Data Cleaning and preparation.

• Exploratory data analysis.

• Model building and deployment.

Some Remarkable Breakthroughs in Data Science

Still being an emerging technology, data science has an enormous scope to grow larger. The latest discoveries and trends have set it apart from major professions in ways more than one. The following are emerging trends in Data Science:

1. Artificial Intelligence

2. Cloud Services

3. AR/VR Systems

4. IoT

5. Big Data

6. Automated Machine Learning

7. Quantum Computing

Are We Alone in the Universe?

This was the title of an opinion essay penned by none other than Winston Churchill, the well-known former prime minister of England, who was an advocate of science. In the article, Churchill agrees with other scientists of the time and now, that life in other parts of the universe is probable but Earth-like life will require Earth-like conditions. In December 2017, Google developed and applied data science algorithms on data or signals collected by NASA's Kepler telescope, to identify a Solar System like our own called the Kepler-90 star system elsewhere in the universe. Similar to our Solar System, the Kepler-90 star system, which is 2,200 light years away, houses 8 planets and may potentially house Earth-like conditions in some of its planets.

The Emergence of Artificial Intelligence (AI)

Marketers appear more hesitant about the immediate benefits of AI compared to other sectors, such as medicine and manufacturing, where it has been deployed to make highly significant and consistent detections of cancers or engineering defects. Likewise, financial services see benefits in improving the effectiveness of commercial and personal lending decisions where incremental improvements in modelling can add millions to the bottom line. But marketing will benefit. AI opens up the opportunity for more marketers to undertake data analysis and predictive modelling efficiently and effectively without the need for large data science teams.

The Data Science Life Cycle

Following is a brief description of how a Data Science problem is solved.

Defining and Understanding the Problem:

One of the most important steps is identifying the major problem or the setback or the issue faced by the client. It is important to find a clear objective for implementing the following steps. In short, it is important to know the business objective early since it will decide the final goal of the analysis.

Data Collection:

Data Collection is the next stage in the data science life cycle to collect raw data from relevant sources. The data can be collected in structured or unstructured form. Data is collected from social media, blogs from websites, data from online repositories, and even data streamed from online sources via APIs, web scraping, or data that could be present in Excel or any other relevant and reliable resource.

Data Cleaning and Preparation:

In this stage, the data collected is organized and stacked to prepare it for data analysis and further steps. It is one of the most time-consuming stages and one of the most significant stages too. It involves changing the organization of data to a more useful form and clearing the non-useful entries from the data. Cleaning data is a logical process. Proper knowledge of various cleaning methods is required to perform it successfully.

Exploratory Data Analysis:

Exploratory Data Analysis is another critical step in the data lifecycle. There are no set guidelines for this methodology, and it has no shortcuts. The key aspect to remember here is that your input determines your output. The data prepared from the previous stage will be explored further to examine the various features and their relationships.

Experts use data statistics methods such as mean and median to better understand the data. In addition, they also plot data and assess its distribution patterns using histograms, spectrum analysis, and population distribution. Depending on the issues, the data will be analyzed.

Model Building and Deployment:

This is the final stage of the data lifecycle. On the clean and well-structured data, we apply different Machine Learning Algorithms and use charts and statistics to represent the desired outcomes and answer the objective question.

The selection of the optimal algorithm for a given dataset is done by the following steps.

• Understand the goal of your project.

• Analyze your data by its size, value type, and nature of data.

• Understand and consider the speed and training time of your model.

• Find out the linearity in data and check for correlation.

• Experiment with features and parameters.

At last, the ultimate goal is to fit such a model with or without tuned hyperparameters to get the highest accuracy and most stability of all or a model with the optimal accuracy and stability when new data is given to the model for prediction.

After this is done we come to the end of a data lifecycle. At last, we use statistical tools charts, and graphs to visualize data. It is vital to study statistics in detail because these outcomes can be used to our benefit

Data Science in Real Life

Now after having a basic idea of how Data Science problems are dealt with and solutions are taken out let’s discuss some of the applications of Data Science in real life.

One of the most successful applications of data science technology and machine learning algorithms is Instagram.

Instagram

Emerging as one of the most used social media applications, Instagram uses multiple algorithms to make its users stay on the app longer by delivering content users find interesting and relevant.

Instagram algorithms focus on Who, What, and When

Who

Whose post are you interacting with? It finds patterns in whose content you watch more and whose posts you like.

What

What type of content do you engage most with? For example, if you love Technology it will keep serving you that content.

When

This focuses on the time of the day the content was posted to decide if it is relevant to you. It also considers how often you scroll on the app and understands the pattern in daily usage to push relevant content at times.

The ultimate goal of the Instagram algorithm is to make Its users stick to the app and spend more and more time on the app.

HealthCare

There is rapid development in health care due to data science. This field is evolving quickly by taking advantage of advanced-level machine learning and data analytics. Data science applications are far-reaching, especially in patient care, pharmaceuticals, etc.

Here are some of the top data science use cases in health care.

• Discovering Drugs The major contribution of data science is to provide the groundwork for the synthesis of drugs using AI. With the help of AI Mutation and addressing more specific diseases can be done more conveniently.

• Virtual Assistance Chatbots and AI platforms created by data scientists are used by people to get immediate diagnoses by entering certain information or answering relevant questions.

• Wearables The phenomenon of the Internet of Things (IoT), which ensures maximum connectivity, is a blessing to data science. Nowadays fitness bands and smartwatches are used to track and manage their health.

• Tracking Patient Health Do you know the human body generates 2TB of Data DAILY? The wearable devices allow doctors to collect most of this data like heart rate, glucose levels, sleep patterns, stress levels, and even brain activity. With the help of data science tools.

A simple example of how data science can be used in health care is given below. Here is a web app that takes Glucose levels, BP, Insulin Value, BMI value, and age as values to predict if a person has diabetes.

Diabetes Prediction

Just so you know, the web app linked is just a prototype and is not actually advisable to use for medical diagnosis in any circumstances. It can only be used for academic and learning purposes.