Milan Ajudiya

Data Scientist

Ahmedabad, Gujarat, India4 yrs 10 mos experience

Most Likely To SwitchAI ML Practitioner

Key Highlights

Expert in Natural Language Processing and Machine Learning.
Proven track record in data visualization and analytics.
Strong collaborative skills driving cross-functional projects.

Stackforce AI infers this person is a Data Scientist specializing in AI and Business Intelligence.

Contact

Skills

Core Skills

Natural Language Processing (nlp)Deep LearningData AnalysisData VisualizationMachine LearningPredictive ModelingBusiness Intelligence

Other Skills

AlgorithmsAmazon Web Services (AWS)Analytical SkillsArtificial Intelligence (AI)Big DataBusiness InsightsComputer VisionData AnalyticsData CleaningData PreprocessingData ScienceDockerEDAElbow MethodExtract, Transform, Load (ETL)

About

As Data Scientist I am Proficient in Python, Machine Learning, MySQL, PowerBI and large data handling. A collaborative team player with excellent communication and interpersonal skills, driving effective cross-functional collaboration. Expert at uncovering actionable insights and delivering impactful recommendations. Detail-oriented problem solver, dedicated to accuracy and quality. Passionate about continuous learning and adapting in fast-paced environments.

Experience

4 yrs 10 mos

Total Experience

2 yrs 5 mos

Average Tenure

2 yrs 6 mos

Current Experience

X-byte enterprise solutions

2 roles

Data Scientist

Promoted

Oct 2024 – Present · 1 yr 8 mos · Ahmedabad, Gujarat, India · On-site

Fine-tuning LLaMA models and other large language models (LLMs) using Hugging Face, optimizing performance for
various NLP tasks.
Developed project for text summarization, and retrieval-augmented generation (RAG).
Leveraged LangChain for building scalable AI applications, improving chatbot and virtual assistant functionalities.
Built and optimized vector databases (ChromaDB, AstraDB) for efficient retrieval-based AI applications.
Integrated LLMs into real-world applications using LangChain and Flask, enabling seamless deployment of AI-powered
solutions.

DockerBig DataNatural Language Processing (NLP)AlgorithmsDeep Learning

Data Analyst

Nov 2023 – Sep 2024 · 10 mos · Ahmedabad, Gujarat, India · On-site

Developed 10+ dynamic Power BI dashboards and custom reports, enhancing data visualization and enabling data-driven decision-making for clients across various industries.
Utilized statistical analysis and machine learning techniques to transform complex datasets into actionable insights,
resulting in a 20% increase in operational efficiency for clients.
Created interactive data visualizations that improved engagement, leading to a 30% reduction in reporting time.
Collaborated with cross-functional teams to fulfill business needs and contributing to a 10% growth in client satisfaction

SQLImage ProcessingMachine LearningMicrosoft ExcelLinear AlgebraMicrosoft Power BI+27

Railofy

Data Analyst

Jan 2023 – May 2023 · 4 mos · Mumbai, Maharashtra, India · Remote

Tracked and interpreted daily ticket booking data across 10,000+ transactions, ensuring 100% accuracy through effective cron job management.
Leveraged BI tools to create comprehensive reports and visualizations, improving decision making and operational efficiency by 5%.
Collaborated on machine learning project, focusing on hyperparameter tuning that enhanced model performance by up to 20%.

SQLLinear AlgebraMicrosoft Power BIStatisticsPandas (Software)Keras+18

Almabetter

5 roles

Online Retail Customer Segmentation

Jul 2022 – Aug 2022 · 1 mo

Developed a Clustering model using K-means to identify major customer segmentation present in data to optimize the impact of marketing campaign.
Performed Feature Engineering to obtain new feature such as RFM (Recency, Frequency, Monetary) to get more details about customer's purchasing behavior.
Evaluated the optimal clusters using Elbow method and Silhouette Score.
Optimal clusters obtained is 3 for customers, which could be further used in various use cases like marketing campaigns and customer targeting.

Mobile Price Range Prediction

Jun 2022 – Jul 2022 · 1 mo

Developed a Classification model using Supervised Learning Techniques to predict Mobile price range to increase the sales in competitive Mobile phone market.
Performed EDA and monitored the trend & feature correlation to check the relationship of features which drives the Price of a mobile.
Support Vector Machine classifier appeared to be the classifier on the given data, also performed GridsearchCV based Hyperparameter Tuning to obtain optimal parameters for the model.
SVM classifier achieved an accuracy of 97.3%, which leads to increase in overall sale of the mobile phones.

Appliances Energy Prediction

May 2022 – Jun 2022 · 1 mo

Leveraged Supervised Learning techniques to build a regression model to predict appliances energy consumption of certain buildings in Belgium using periodic sensor data and local weather.
Employed pre-processing techniques such as feature scaling to obtain all features on a same scale, outlier treatment, missing value imputation and removed multicollinearity using VIF.
Random Forest Regressor appeared to be the best regressor, performed Hyperparameter tuning using GridSearchCV to obtain optimal parameters of the model.
Random Forest Regressor achieved an R-Square Score of 0.56 on test Data, that helps in saving the Energy Consumption of the area.

Hotel Booking Analysis

Apr 2022 – May 2022 · 1 mo

Exploratory Data Analysis is used to see what the trend and which features are are important and visualize the data by different types of graphs.
Dataset contains more than 1 lakh rows and 32 features/Columns both numerical and categorical values.
Data preprocessing, Fix the null values and clean the dataset, detect outliers and treat them, and done EDA by using different kinds of graph.