Feature Value of a product (Personal Computers and Printers)

 Understand business problem, analyze data & provide impactful data-backed solutions using Statistics, ML & DL frameworks

 Analytics project in functions of Marketing, Supply-Chain, Order management & End Customer

• Customer Preference for product renewal: Ordered logistic regression is used to classify the customer preference towards the renewal of Product. POC to provide real time solution for customer care in insurance domain.POC to identify major issues in Insurance laps. POC on Attrition, Customer Life Time Value, Cross Sell and Upsells. Learning and using IBM Watson tools (Watson Knowledge studio, Watson Analytics), Ordered logistic regression, Logistic Regression.

• Return to Market:Built different binary classification models and identified the best model based on accuracy to know the customers who are returning to market in six months. Used machine learning algorithms to classify in which month the customers are returning to market • Disposal Days – Used machine learning algorithms to classify in how many month the customers are keen to sell it. • Fleet capacity forecast: the ARIMA /ARIMAX algorithms were deployed to forecast the retiring fleet of globe and mathematical equation is used calculate forecasted fleet. • Port calls Prediction: Using the existed trade forecasts the mathematical ratios were applied to forecast an port calls for next 50 years.• Asset Valuation: Built the Regression analysis for forecast of valuation of new ships and used ships.Expertise:• Extremely comfortable and proficient in undertaking statistical analysis using tools like SQL, R etc.,• Used Bigdata tools Hadoop, pig, hive to deploy the developed models on full data• Key competencies: Exploratory data analysis, Modelling techniques, Machine Learning techniques, Forecasting etc.,

• Sales Prediction: Built the Regression analysis for prediction of sales of a non-cooperator stores• Customer Response Model: Built response models based on campaign data to classify customers based on their preference.• Customer Segmentation: Implemented cluster analysis to profile the customer base, and to identify niche target segment based on behavioral characteristics for a new product launch of a major stationery company• Forecasting the sales: Implemented ARIMA procedure to forecast the sales of a products.• Retail Management Survey: Key responsibilities –o To maintain and calculate the sample size using techniques like random sampling, stratified samplingo To compute the projection factor – universe, sales, and day adjustment factors, for precise representation of the universe o Analyze trends in sales using client specific software and check the behavior of each product over time.o Create and maintain exhaustive reports of sales data for the entire market grouped by retail structures