Skip to main content

Power BI Sales & Inventory Forecasting Project (SARIMA)

Project Overview

In this project, I built an end-to-end Business Analytics & Data Science solution using SQL, Power BI, and Python to:

  • Analyze historical sales, profit, discounts, and units sold

  • Build an Executive Summary Dashboard for leadership

  • Forecast next 3 months of Sales & Units Sold

  • Support inventory planning and business decision-making

This project simulates a real-world eCommerce / Retail analytics use case, combining ETL, BI reporting, and predictive modeling in a single workflow.

Business Objective

Primary Goals

  • Provide leadership with a single-source executive dashboard

  • Identify sales, profit, and regional performance trends

  • Predict future demand (Sales & Units Sold) for:

    • Inventory planning

    • Revenue forecasting

    • Procurement & supply-chain readiness

Key Questions Answered

  • How are sales and profits trending over time?

  • Which regions and segments drive the most value?

  • What will be the expected sales & unit demand for the next 3 months?

Architecture & Tools Used

LayerTools
Data SourceSQL Database (simulated enterprise retail DB)
ETL & TransformationSQL, Power Query
Analytics & BIPower BI
ForecastingPython (SARIMA – statsmodels)
VisualizationPower BI + Python visuals
Skills DemonstratedSQL, ETL, Time Series, BI, Forecasting

Step 1: Data Extraction (ETL using SQL)

I started by extracting structured sales data using SQL from the transactional database.

Sample SQL ETL Query

SELECT  
    OrderDate,
    Country,
    Segment,
    Product,
    Sales,
    Profit,
    Discounts,
    UnitsSold,
    COGS
FROM Financials
WHERE OrderDate IS NOT NULL;

ETL Objectives

  • Select only business-relevant fields

  • Ensure date integrity

  • Prepare data for analytics & forecasting

Step 2: Data Cleaning & Transformation

Cleaning Actions

  • Removed duplicate rows

  • Handled null values

  • Standardized column names

  • Converted Month text → Month Number

  • Ensured consistent date format

Created a Date Dimension Table

Essential for:

  • Time intelligence (YoY, MoM)

  • Filtering by Year / Month / Quarter

DateTable =
ADDCOLUMNS (
    CALENDAR (DATE(2013,1,1), DATE(2015,12,31)),
    "Year", YEAR([Date]),
    "Month", FORMAT([Date], "MMMM"),
    "Month Number", MONTH([Date]),
    "Quarter", "Q" & FORMAT([Date], "Q")
)

Step 3: Executive Summary Dashboard (Power BI)

Dashboard Purpose

Designed for CXOs & Business Heads to get instant insights.

Key Visuals

  • 📈 Profit Trend by Date

  • 🌍 Profit by Country (Map)

  • 📊 Sales by Segment & Date

  • 🎛️ Interactive slicers (Year, Month)

Business Value

  • Quick performance monitoring

  • Region-wise profit analysis

  • Segment contribution clarity

Step 4: Predictive Analytics – Sales & Units Forecast

To support inventory and revenue planning, I built a 3-month forecast using SARIMA.

Why SARIMA?

SARIMA (Seasonal ARIMA) is ideal for retail/ecommerce data because:

  • Handles trend + seasonality

  • Works well with monthly sales patterns

  • Provides confidence intervals (risk visibility)

SARIMA Components

  • AR (p): Autoregression

  • I (d): Differencing (trend removal)

  • MA (q): Moving average

  • Seasonal (P, D, Q, s): Monthly seasonality (s = 12)

Step 5: Python SARIMA Forecast (Power BI Python Script)

Key Python Steps

  1. Convert Month text → numeric

  2. Create proper Date column

  3. Aggregate monthly sales

  4. Train SARIMA model

  5. Forecast next 3 months

  6. Plot actual + forecast + confidence band

Simplified SARIMA Code

from statsmodels.tsa.statespace.sarimax import SARIMAX

model = SARIMAX(
    monthly_sales['Units_Sold'],
    order=(1,1,1),
    seasonal_order=(1,1,1,12)
)

model_fit = model.fit()
forecast = model_fit.get_forecast(steps=3)
conf_int = forecast.conf_int()

Step 6: Predictive Visualization in Power BI

Forecast Dashboard Includes

  • Actual historical trend

  • Forecasted next 3 months

  • Upper & lower confidence limits

  • Separate visuals for:

    • Units Sold

    • Sales Value

Business Impact

  • Better inventory planning

  • Reduced stock-out risk

  • Data-backed procurement decisions

Insights & Outcomes

Key Insights

  • Clear seasonal demand patterns

  • Certain months show predictable spikes

  • Forecast confidence helps risk planning

Business Value Delivered

  • Executive-ready reporting

  • Predictive decision support

  • Scalable analytics framework

Skills Demonstrated

  • SQL & ETL pipelines

  • Power BI data modeling

  • DAX & Date intelligence

  • Time-series forecasting

  • Python scripting in Power BI

  • Business storytelling with data





Comments

Post a Comment

Popular posts from this blog

Using NLP for Text Analytics with HTML Links, Stop Words, and Sentiment Analysis in Python

  In the world of data science, text analytics plays a crucial role in deriving insights from large volumes of unstructured text data. Whether you're analyzing customer feedback, social media posts, or web articles, natural language processing (NLP) can help you extract meaningful information. One interesting challenge in text analysis involves handling HTML content, extracting meaningful text, and performing sentiment analysis based on predefined positive and negative word lists. In this blog post, we will dive into how to use Python and NLP techniques to analyze text data from HTML links, filter out stop words, and calculate various metrics such as positive/negative ratings, article length, and average sentence length. Prerequisites To follow along with the examples in this article, you need to have the following Python packages installed: requests (to fetch HTML content) beautifulsoup4 (for parsing HTML) nltk (for natural language processing tasks) re (for regular exp...
Post a Comment
Read more

NumPy and Pandas for Data Science: A Comprehensive Guide

In the world of Data Science , working with large datasets, performing data manipulation, and analyzing numerical information is a fundamental task. To make these tasks easier and more efficient, Python has two powerful libraries: NumPy and Pandas . These libraries are widely used for data manipulation, analysis, and visualization and are crucial tools for any data scientist. Let’s take a deep dive into both NumPy and Pandas , exploring their functionality and how they empower data scientists to work smarter and faster. 1. What is NumPy? NumPy (Numerical Python) is an open-source library used for numerical computing in Python. It provides support for working with large, multi-dimensional arrays and matrices, and offers a wide range of mathematical functions to operate on these arrays. Key Features of NumPy: Efficient Array Operations: NumPy arrays, or ndarrays , are far more efficient in terms of memory and computational speed compared to Python’s native lists. Vectorizati...
Post a Comment
Read more

Understanding Neural Network Models for Regression: ANN, RNN, and CNN

In the world of machine learning, neural networks play a crucial role in solving complex problems. They have shown remarkable performance in various domains, from image classification to natural language processing. However, one of the fundamental tasks that neural networks can perform is regression —predicting continuous values based on input features. In this blog post, we'll explore three types of neural network models— Artificial Neural Networks (ANN) , Recurrent Neural Networks (RNN) , and Convolutional Neural Networks (CNN) —and discuss how they can be used for regression tasks. Additionally, we'll walk through code examples and explain how to train these models for regression problems. What is Regression? Regression is a type of supervised learning where the model is trained to predict continuous values. Common examples of regression tasks include predicting house prices, stock market trends, or temperature forecasting. The primary goal is to find the best-fit line (...
Post a Comment
Read more