6.

References
A STRIDE CASE STUDY
4. Product & Solution

2. Problem Statement

5. Our Values

1. Team 3. Problem Statement

Introduction
 MEET VAKANI
Meet the Team A11 Project Manager, ML Development

CHAITALI JAWALE

Software & ML Development

PRACHI

Data Analytics & Visualization

Project Advisor: Dr. Molham Chikhalsouk
 Target Audience

Small and Medium-sized Enterprises (SMEs)
We provide an accessible and cost-effective solution for
SMEs to leverage data analytics, gain valuable insights, and
make data-driven decisions without extensive technical
expertise.
Large Enterprises with Diverse Data Sources
Our platform seamlessly integrates with complex data
ecosystems, consolidates data from multiple sources, and
generates comprehensive insights to support strategic
decision-making and operational optimization.
It is transportation solutions provider. Which ships via 3 means of Transport – Road, Flight
& Ship.

• Customer Data – Gender, Rating, prior_purchases

• Shipment Data – Warehouse_block, Mode of Shipment, Weight, reached on time
• Financial Data – Cost & Discount offered

Vision
To be a leader in delivering innovative and data-driven logistics solutions
 A Stride Case Study
Business Problem 2023
The Stride logistics industry faces challenges in
Extracting Insights
optimizing operational efficiency and enhancing
customer satisfaction due to limited insights
Operational Efficiency
derived from shipment data.

Customer Satisfaction
Why?

1. Limited visibility into delivery time and customer

rating for performance evaluation.
2. Inefficient query response management impacting
customer experience.
3. Difficulty in determining the impact of product
importance on delivery time and customer ratings.
WHAT WE’RE TRYING TO SOLVE FOR STRIDE LOGISTICS ?
Let's dive into the details of our project. We are focusing on three key questions related to customer
satisfaction and delivery efficiency

Product Delivery Query Resolution Ratings

Was the product delivered on the If the product importance is high, does it
expected time, and what was the Was the customer's query answered? have the highest rating or was it
customer rating? delivered on time?
 Product - Workflow

Data Collection: Gather relevant shipment data from various sources.

Data Preparation: Cleanse and transform the data for analysis.

Data Analysis: Apply advanced analytics techniques for insights.

Reporting & Visualization: Present findings in clear reports with

visualizations.

Recommendations & Action: Provide actionable insights for

improvement.
1. Understand the data – thoroughly via Data Analysis (numerical, categorical values)

Warehouse block The Company have big Warehouse which is divided in to block such as A,B,C,D,E.
Mode of shipment The Company Ships the products in multiple way such as Ship, Flight and Road.

Customer care calls The number of calls made from enquiry for enquiry of the shipment.
The company has rated from every customer. 1 is the lowest (Worst), 5 is the highest Cost of
Customer rating
the Product in US Dollars.
Cost of the product
The Number of Prior Purchase.
Prior purchases
The company has categorized the product in the various parameter such as low, medium,
Product importance
high.
Gender Male and Female.
Discount offered Discount offered on that specific product.
Weight in gms It is the weight in grams.

Reached on time It is the target variable, where 1 Indicates that the product has NOT reached on time and 0
indicates it has reached on time.
Our Project Phases

Phase 1

Phase 2

Phase 3
 Phase1 : EDA Observations 2
1
5

4
Phase1 : EDA Observations: Univariate Analysis
Phase1 : EDA Observations: Bivariate Analysis, Focusing on correlation
1. It shows a significant positive
association with Discount_offered.

2. Very Weakly positive

correlations exist between the
target variable,
"Reached.on.Time_Y.N," and
customer_care_calls, customer
ratings, ost_of_the_product, and
prior_purchases.

3. On the other hand,

weight_in_gms has a rather
significant negative association.
Phase1 : EDA Observations: Bivariate Analysis, Focusing on correlation
As we have very weak correlation with the existing estimated feature vs reached on time variable, we have to understand the data properly by using some metrics and
understanding the data.

1. Most products are in the "dcat1" category, with a count of 7492, indicating
that this is the most common discount category.
2. "dcat2" follows with 1298 products, representing a smaller count than "dcat1"
but still relatively significant.
3. Categories "dcat5," "dcat6," "dcat3," and "dcat4" have counts ranging from
507 to 465, indicating a moderate presence of products in these discount
categories.
4. "dcat7" contains 287 products, representing a lower count compared to the
earlier categories.
"dcat8," "dcat9," and "dcat10" have no products. might be they will add it in
future, indicating that there are currently no items in these discount categories.

But still, we don’t have correlation

to proceed. So, whats the next step?
Phase 2 : Feature Engineering – Data Preprocessing
Phase 2 : Feature Engineering – Correlation Analysis
What’s more unique than this?
Our USP : Unleashing the Power of Data for
Stride Logistics

Comprehensive data analysis using advanced

algorithms and machine learning

Real-time visibility and insights for optimized

operations

Actionable recommendations tailored to address

Stride's unique challenges

User-friendly interface for easy navigation and data

interpretation

Scalable solution that integrates with existing

systems

Empowering Stride Logistics with data-driven

decision-making and competitive advantage
 Excellence
Adding values to Business!
Our Mission Our team of experts is
dedicated to delivering high-
quality solutions, precise
analysis, and actionable
insights that bring tangible
Ultimately, our solution drives improved business value to your business.
performance, competitiveness, and long-term success
for Stride Logistics.

Innovation Integrity
We embrace We uphold the highest
innovation and ethical standards in all
leverage cutting-edge aspects of our
technologies to stay at business. Trust and
the forefront of data integrity are the
analytics. foundations of our
relationships with
clients.
References:

• Stride Logistics. (n.d.). About Us. Stride Logistics. Retrieved

https://www.stridelogistics.com/about/

• ArXiv Paper:
A Large-scale Dataset for Recognizing Packaging Works in IoT-enabled Logis
tic Environments

• Medium Article: Simple Data Cleaning and EDA for a Baseline Logistic Regression.
Medium. Retrieved from link
 Woof
y
financ our way to
i a l suc
u s be y c e s s - l e t
o ur
c om pa l oy a l
ni o n !

That’s a Wrap,
Any questions?