Original Automotive Analytics Case Study

German EV Market Analysis

Analysing battery electric vehicle registrations, manufacturer competition, model performance and EV portfolio expansion in Germany between 2020 and 2026

Python • Pandas • Matplotlib • Seaborn • KBA Data • Data Cleaning • Data Validation • Market Analysis • Competitive Analysis • Exploratory Data Analysis

This case study examines Germany's battery electric vehicle market using official registration records from the German Federal Motor Transport Authority (KBA). The registration data was enriched with a verified EV model mapping database containing canonical model names, market-entry information, model status, mapping confidence and official manufacturer sources.

Explore Case Study View Kaggle Notebook →

Project Overview

Business Area

Automotive analytics, electric mobility and competitive market intelligence

Cleaned Dataset

3,334 unique EV registration records after removing 40 exact duplicates

Market Coverage

Germany's leading EV manufacturers, verified model series and reporting years from 2020 to 2026

Main Tools

Python, Pandas, Matplotlib, Seaborn, Excel and official KBA data

Business Problem

Germany's transition toward electric mobility has intensified competition among established automotive manufacturers and dedicated electric vehicle companies. Registration totals alone do not explain which manufacturers are leading, which models are driving adoption or how product portfolios have evolved.

This project transforms official registration data into business insights that can support market monitoring, product strategy, competitive benchmarking and data-driven decision-making.

Key Business Question

How has Germany's battery electric vehicle market developed between 2020 and 2026, and which manufacturers, models and vehicle segments have contributed most strongly to its growth?

Dataset

The project uses an original analysis-ready workbook created by merging KBA registration records with a verified electric vehicle model mapping database. The enrichment process standardised model identities and added official manufacturer references, launch information and confidence levels.

Registration Metrics

Total registrations and BEV registrations by manufacturer, model series, segment and reporting year

Verified Model Data

Canonical EV names, production or reveal start, German market year and model status

Data Quality Fields

Mapping confidence, merge status, verification notes and official manufacturer source

Analysis Type

Descriptive, exploratory, time-series, competitive and product portfolio analysis

Analytical Process

The project follows a structured workflow from source preparation through market interpretation and strategic recommendations.

STEP 01

Prepare

Loaded the merged KBA and verified EV model database.

→

⌕

STEP 02

Inspect

Reviewed structure, types, missing values and statistics.

→

✓

STEP 03

Clean

Investigated quality issues and removed exact duplicates.

→

STEP 04

Analyze

Examined trends, brands, models, share and segments.

→

▥

STEP 05

Compare

Evaluated growth and competitive performance.

→

◎

STEP 06

Recommend

Converted findings into business recommendations.

Behind the Analysis

Open each stage to explore the Python workflow, screenshots and reasoning.

STAGE 01Set Up and Load the DatasetLibraries were imported and the merged EV workbook was loaded.+

Preparing the Python Environment

ev_market_analysis.py

import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns

file_path = "/kaggle/input/datasets/ashwinraphel/german-ev-registration/German EV Registration Database 20202026.xlsx"

df = pd.read_excel(
    file_path,
    sheet_name="Merged Monthly EV Data"
)

Import Libraries

Load Dataset

STAGE 02Understand the DatasetStructure, records, data types, missing values and numerical distributions were reviewed.+

Inspecting Dataset Structure and Quality

inspect_dataset.py

df.head()
df.info()
df.isnull().sum()
df.shape

missing = (
    df.isnull()
      .sum()
      .sort_values(ascending=False)
)

df.describe()
df.sample(10)

Dataset Preview

Dataset Information

Initial Missing-Value Check

Dataset Shape

Data Types

Sorted Missing Values

Statistical Summary

Random Sample

STAGE 03Validate and Clean the DataNegative-value and duplicate checks were completed before creating the cleaned dataset.+

Resolving Data-Quality Issues

Validate Values

No negative BEV or total registration values were found.

Identify Duplicates

The initial check detected 40 exact duplicate records.

Inspect Records

Duplicate rows were reviewed before removal.

Create Clean Dataset

The final dataset contained 3,334 unique rows and zero duplicates.

Data Quality Validation

Investigate Duplicate Records

Remove and Validate Duplicates

STAGE 04Explore the German EV MarketTrends, manufacturers, models, market share and vehicle segments were analysed.+

Market Overview and Product Performance

STAGE 05Compare Competitive PerformanceYoY change, manufacturer rankings, heatmap patterns and growth were evaluated.+

Advanced Competitive Analysis