Looking at the business cases of Telecom, Retail, Finance, Health care, their Core Predictors, & the approaches to solve them!

Hello Everyone! The objective of this story is to look into the business problem first, and then the problem statement, followed by the required data elements for predictions, Regression functions how it can help solve them.

We will take 2–3 business problem cases from different industries (Retail, Telecom, Finance, Health Care) and then take a look into the intricacies of the problem and apply the appropriate regression solution.

Let’s look into the Business problems:

Retail/Manufacturing/Telecom: Predict Revenue, Sales, Costs, Demand.

Business problem could be to improve the profit of the company. All of these factors — revenue, sales, costs, demand help to achieve either more revenue or reduce costs to achieve or surpass the forecasted numbers and make the company profitable. Demand forecasts helps to plan and maintain the optimal number of stock inventories (and to boost sales ) to meet the market demand.

Finance: Predict Stock Risks/Volatility.

Business problem could be to identify stocks that can be fit for recommendation (Eg: Buy, Sell, Hold Calls) thereby enhancing customer engagement of a finance agency.

Health Care: Predict health care of patients.

Business problem could be to predict the likelihood of recovery from the disease (Eg: Covid-19).

Let’s write the Problem Statements:

Retail/Manufacturing: Predict Daily demand/sales (eg: dairy products) so that products inventory can be maintained as only required.Telecom: Predict Broadband Fibre, Digital TV services sales during coming christmas season or next month so that more network capacity can be added and investment planning as accordingly.Finance: Predict stock volatility so that stock financial advisors can make the recommendations for their customers to invest on them.Health Care: Predict recovery time of disease (eg: covid-19 recovery time) based upon treatment, inoculation history, patient medical history, age, personal & other factors.

Quick Look at Regression Types:

Linear Regression plots the line of best fit linearly based upon the data point observations. This is basic ML model and we have many stories explaining about this, I do not want to go in depth of solving these solved models. We will look at how our approach for the problem and choose the right one so that we can fit them appropriately with our business cases.

Type of Regression depends upon the number of feature variables or predictors & their linear relationship function.

Finding out the relationships of dependent with Independent variable(s):

If one only independent variable for the prediction — Simple Linear Regressiony = mx + b + e whereas x is the independent variable used to predict; y is the dependent variable to predict; b is the y intercept; m is the slope of the explanatory variable; e is the residual error termIf more than independent variable — Multiple Linear Regressiony = m1x1 + m2x2 + m3x3 + … + mtxt + b + e whereas x1,x2..,xt are the independent variable used to predict; y is the dependent variable to predict; b is the y intercept; m1,m2,m3..mt are the slope of the explanatory variable; e is the residual error termIf the relationship equation having polynomials functions — Polynomial Regressiony = m1x1 + m2x1 ^2 + m3x1 ^3 + … + mtx1 ^t + b + e whereas x1 is the independent variable used to predict; y is the dependent variable to predict; b is the y intercept; m1,m2,m3..mt are the slope of the explanatory variable; e is the residual error term

Finding out the movement & relationship with time:

If the Predicted variable is same as independent, and variable moves by itself with time — Auto Regression.This is the Time Series Model Approach. Many classical time series model intuiting from this basic concept with slightly different approaches (ARIMA, SARIMA, SARIMAX..) taking moving average or Autoregressive, or integrating them together, + adding seasonal component to it.

Choosing the right approach for our use cases:

Manufacturing: Predict Daily sales (eg: dairy products) so that products inventory can be maintained as only required.

List of characteristics of a dairy farm that can impact the daily production quantity or the sale quantity:

Land Area of the farm
Farm Size — Large/Medium/Small
Number of cows
Product Type: Milk/Yoghurt/Cheese
Shelf Life: Number of days product remain usable
Storage Condition: Frozen/Refridgerated

Solution: Multiple Linear Regression Approach to predict Daily Sales quantity — Just fitting these features in the Multiple Linear Regression function above (x1,x2,x3..)

Retail: Predict Daily demand(eg: dairy products) so that products inventory can be maintained as only required.

List of characteristics of a dairy demand for a retail store that can impact the daily production quantity or the sale quantity:

Closeby Retail Stores availability.
Age group bin count of people living around the store.
Ethnicity of customers — A PII variable demands using them as per governance policies.
Product Type
Shelf Life: Number of days product remain usable
Storage Condition: Frozen/Refrigerated
Number of Customers visiting the store/online purchases, ..
Customer Demographics

Solution: Multiple Linear Regression Approach to predict Daily Sales quantity — Just fitting these features in the Multiple Linear Regression function above (x1,x2,x3..)

With Time Series (Auto Regression, and combination of other approaches also possible) also this problem can be attacked, Experiment results would prove the best fit.

Telecom: Predict Broadband Fibre, Digital TV services sales during coming christmas season or next month so that more network capacity can be added and investment planning as accordingly.

List of characteristics of a new BB service sale of a Telecom company that helps the company more profitable, and make the company informed for any investments and increase the network infrastructure helping to improve customer engagement & satisfaction:

Competitor products price.
Competitor products features.
Customer needs & wants (eg: Some customers looking for medical alarms, security alarm — BB service should be able to support the specific needs)..
Customer 360 Data — Age, Demographics, Income & affordability, Customer Affinity & traits.

Solution: Multiple Linear Regression Approach to predict BB Sales for the future period — Just fitting these features in the Multiple Linear Regression function above (x1,x2,x3..).

Finance: Predict stock volatility that pave a way to make the recommendations for their customers to invest on them.Beta helps to calculate the expected return of investments in a stock by applying the CAPM (capital asset pricing model) calculation (calculated values are in the CAGR % per year).As we all know Beta — is one of the most sought after metric to pick a stock to invest — If Beta is higher than 1, the volatility of the stock is higher than the market & also the risk, If Beta is lower than 1, then the stock price volatility lower than the market and are stable and not change drastically with the market movements. If Beta is equal to 1, then the stock price volatility is as same as market volatility.

Beta Calculation Formula using covariance:

Beta=Covariance of the stock with the Market returns / Variance of the market returns Beta Coefficient = Covariance (Rn , Rm) /Variance (Rm)whereas Rn - Return on the Individual StockRm - Return on the Overall Market

List of characteristics to predict Beta value:

Competitor stocks price.
International market fluctuations.
Gold Prices & International Currency value fluctations
Company P/E Price Earnings Ratio
Company Market capitalization
Net Profit, Net Revenue
Debt
Customer Base & Market of the company
Competitor performance
Government Policies
Many other External factors market get impacted

Solution: As many factors involved, we can solve this stochastically, Multiple Linear Regression Approach can be one approach to predict Beta of a stock — Just fitting these features in the Multiple Linear Regression function above (x1,x2,x3..).

Also this can be considered as Non Linear, and can use more advanced algorithms to solve.

CAPM Calculation (Expected Rate of Investment Return):

Expected Rate of Investment Return = Risk Free Return + Beta (Market Return)Market Return = Expected Rate of Return based on Market Premium- Risk Free ReturnNote: These are CAGR % for an yearBeta,& the Expected Rate of Return based on Market premium are the primary variable components.Risk Free Return is more or less flat.Risk Free Return - can be the fixed deposit returnsMarket Return - is the return for the risk taken by investing in a stock - that's why it is a premium return

Health Care: Predict recovery time of disease (eg: covid-19 recovery time) based upon treatment, inoculation history, patient medical history, age, personal & other factors.

List of characteristics of a patient for predicting the recovery time

Domicile of Patient.
Age.
Gender
Comorbidities
Diabetes
HyperTension
Coronary Artery Disease
Inoculation History

Solution: Multiple Linear Regression Approach to predict recovery time of disease — Just fitting these features in the Multiple Linear Regression function above (x1,x2,x3..).

Again all of these MLR cases can also be converted as a classification problem instead Regression by converting the target variable as a discrete one instead of continuous variable and can be solved using advanced Non-Linear approaches as well such as XGBoost, GBTs, Random Forest, ANN, etc, which mostly yield better results (as a classification or Regression).

Also this can be the problem candidate for AutoML (Use Google, Azure or AWS cloud if you want to quickly try with AutoML) to pick and chose the best model that gives best results.

We have reached the end of the story. We have more advanced concepts especially the Loss, Error functions to optimize these models we will cover them in next stories. Stay tuned!

If you like this story, and wanting to subscribe for more, click below https://medium.com/@mskmiba/subscribe

Follow for more such contents around data & analytics, Social Interest and Well-being.

Thanks for reading!

Do follow, clap, and support so that it will help me to write more, spend atleast a min in the story so that your read gets a mark. Cheers!

Business Cases of Regression Problems and how to approach them?