Table of ContentsSummaryIntroductionObjective of the ProjectSpecification of the HypothesisBackground of the DatasetCritical Evaluation of Applicable TechniquesImplementation of the Chosen TechniqueInterpretation of Results - Quantitative Results and Qualitative InterpretationConclusionSummaryThe objective of the project is to discover the relationship between the dependent and independent variable. Know how the entire independent variable influences the dependent variable. The restaurant rating is based on many attributes such as food quality, price, restaurant ambience, whether the restaurant has an online delivery system, whether the restaurant offers table reservation, etc. All these factors will affect the profit of the company because customers will consider these factors. dine at their favorite restaurant. Thus, customer relationship management plays an important role in improving the business profits of any organization. Say no to plagiarism. Get a tailor-made essay on “Why Violent Video Games Should Not Be Banned”? Get the original essayKeywords: CRM, Hypothesis, Sentiment Analysis, Support Vector MachineIntroductionCustomer Relationship Management (CRM) plays a vital role in an organization. To be successful in business, the organization must maintain good relations with the customer. The organization must also have loyal and long-lasting customers so that the business value and profits of the organization increase. The main objective of CRM is to collect all the necessary data related to customers and analyze the data using different data analysis and machine learning techniques. The results of the analytics have several benefits, since the data is related to the customer, the results of machine learning and data analysis can be used to improve the quality of the product, it helps to manage the data related to the customer, customer interaction, customer account management, finding new customers, retaining existing customers, from the analytics we can also find out what exactly are the customer expectations and the organization can improve the quality of the products. This will in turn increase customer satisfaction and business profits of the organization. So, we can say that CRM can be used to improve customer value and relationship. Project Objective With the advent of e-commerce on the Internet, searches on social networks and restaurants have increased significantly. Online reviews of different products, places, and restaurants will have a big impact on company profits because customers will search for online reviews and ratings before purchasing a product or dining at a restaurant. So, customer rating plays an important role in the company's profit. Customer reviews and online restaurant ratings can help improve the quality and standard of the restaurant, thereby improving the profit of the business. Restaurant review is important for online users as it gives an overall rating of the restaurant which includes several factors such as food quality, ambience, price range, whether it offers table reservation , whether it offers online delivery, what type of cuisine, location, etc. .There are several online restaurant search websites where data can be used to predict restaurant customer ratings. I chose “Zomato” which is one of the most popular restaurant search sites. These ratings will be useful for users who go online to the Zomato site to search for the bestrestaurants in town. From the dataset, the customer rating can be categorized using several other parameters which will be explained in the next section. In this project, the restaurant rating given by the customer is classified. Customer ratings and company profitability can be predicted.Hypothesis SpecificationFrom the Zomato dataset, the following hypothesis can be formed: There are several attributes in the dataset, how all the independent attributes of the dataset influence the dependent variable which is the restaurant rating. . To be specific how the restaurant: “Location”, “Cuisine”, “Cost”, “Has table reservation”, “Has online delivery” has an effect on the “review text”. Context of the dataset The dataset has the following attributes such as: Restaurant Name, Restaurant ID, City, Address, Cuisines, Cost for two people, Has a table reservation, Has online delivery, Book now, Proceed to order menu, Price range, Overall rating, Rating color, Rating text and votes. The restaurant name will include the names of all restaurants in a location, the restaurant ID will be unique for all restaurants, the city is used to list all the restaurants in a city, the address will be useful to locate the restaurant in one area the kitchens have a list of all items served in the restaurant, the cost of two gives the total amount for two people. There are other attributes in the dataset which are used to discover the different characteristics of the restaurant. A restaurant may offer table reservations, online delivery, etc., all of these attributes will have a high correlation with the dependent variable that is the rating. If a restaurant has all the features and the quality of the food is very good, then it is likely that the restaurant rating will be high. In other cases the restaurant may not have all the features but it may be that the quality of food is good and the overall price is less so customers would prefer such restaurants and there are chances that the rating will be high for these restaurants. . So, all these attributes together will determine the restaurant rating that will be given by the customer. The rating will help other users who log into the Zomato website. So, the better the restaurant's rating, the higher the restaurant's commercial profit will be. The overall rating is a numerical value on a scale of one to five, with one being the lowest. and five being the highest. The evaluation text is coded as excellent, very good, good, okay. For example, if the restaurant has an overall rating of 4.8, it will be coded as excellent in the rating text. The text of the grade will be the dependent variable because it is a categorical variable, while the overall grade is a continuous numerical value. Critical Evaluation of Applicable Techniques There are different methods to find restaurant ratings using machine learning techniques. These reviews will help users of the Zomato website to choose the best restaurant to dine at. Sentiment analysis was used to find the restaurant rating. Here the sentiment score will automatically rank the restaurant rating to help users or customers choose their best restaurant. Sentiment score can be calculated based on user reviews, keywords will have associated ratings to which a sentiment score will be assigned. It will be helpful to know the tone behind the user. The process can be explained as follows. The dataset here is taken from the Yelp site, approximately 100,324 reviews for 2,000 restaurantsare taken into account. Reviews contain many words like good, bad, excellent, wonderful, amazing, wonderful, horrible, terrible, etc., from all these words the sentiment score is calculated. The sentiment analysis process is described below: Firstly, reviews are divided into separate sentiment words, there will be a text file consisting of positive and negative words and each word will have a corresponding sentiment word, as shown in the table above, so the final sentiment score will be calculated. Once the sentiment words are calculated, the emoticons are identified. Let's take an example of two sentences to understand the emoticon identification "the food was excellent" and "the food was excellent", the first sentence will have a higher score compared to the second sentence because the user mentioned the positive review. The sentiment score is calculated by the average of all positive and negative scores. A neutral score is also calculated. The sum of all scores will give the sentiment score. Finally, the score is calculated. The following hypothesis can be assumed: If the food is liked by the customer, the rating will be better for a restaurant. The ambiance of a restaurant plays an important role in a restaurant's rating. The grade will be higher. whether the restaurant's service is good. The price of the restaurant also plays an important role in restaurant rating. There are other techniques to implement sentiment analysis. We can see that techniques such as Naïve Bayes, Support Vector Machines, Decision Tree, K-Nearest Neighbor Classifier, Winnow Classifier, Adaboost Classifier are used. Implementation of the chosen technique The dataset downloaded from Kaggle needs to be pre-processed before applying machine learning algorithms to as the dataset will contain unwanted noise, missing values, null values ​​and special characters. There were many unwanted rows and columns in the dataset, such as country code, detailed locality, latitude, longitude, and currency. These attributes are removed before applying machine learning because these independent variables do not have much effect on the dependent variable. There were other missing and null values ​​in the dataset which were cleaned up in R using the gsub function and removed manually from Excel. From the below output obtained from R studio, we can find the correlation between the different attributes obtained from the dataset. Correlation can be classified into different types, highly correlated, uncorrelated and neutral correlation. Attributes that have 0 have no correlation. Attributes from 0 to 0.5 have a neutral correlation. Attributes from 0.5 to 1 are highly correlated. From the above, let's take an example of a highly correlated attribute, "Price range" and "has a table reservation" are highly correlated. “Offers online delivery” and “offers table reservation” have a neutral correlation with each other. There are several techniques to rank restaurant rating using machine learning algorithms. Rating scores can be calculated using the sentiment analysis we saw previously. The classification support vector machine for restaurant rating is implemented, the method implemented for this project has additional attributes to improve the accuracy rate of restaurant rating classification. Additional attributes include whether the restaurant offers table reservation, offers online delivery, delivers now, moves to menu option, price of food in the restaurant, total votes of the.