diff --git a/edsa_recommender.py b/edsa_recommender.py
index f1192112..a59cc3b7 100644
--- a/edsa_recommender.py
+++ b/edsa_recommender.py
@@ -31,12 +31,33 @@
 # Data handling dependencies
 import pandas as pd
 import numpy as np
+import requests
+from PIL import Image
+from streamlit_lottie import st_lottie
+
 
 # Custom Libraries
 from utils.data_loader import load_movie_titles
 from recommenders.collaborative_based import collab_model
 from recommenders.content_based import content_model
 
+movie_image = Image.open(r'resources/imgs/Movies_AI.webp')
+logo_a= Image.open(r'resources/imgs/lens.jpeg')
+
+def load_lottieurl(url):
+	r = requests.get(url)
+	if r.status_code != 200:
+		return None
+	return r.json()
+
+# Load your raw data
+raw_m = pd.read_csv("resources/data/movies.csv")
+raw_r= pd.read_csv("resources/data/ratings.csv")
+
+#load lottie urls
+data_lottie = load_lottieurl("https://assets7.lottiefiles.com/packages/lf20_8gmx5ktv.json")
+info_lottie = load_lottieurl("https://assets1.lottiefiles.com/packages/lf20_HhOOsG.json")
+
 # Data Loading
 title_list = load_movie_titles('resources/data/movies.csv')
 
@@ -45,7 +66,7 @@ def main():
 
     # DO NOT REMOVE the 'Recommender System' option below, however,
     # you are welcome to add more options to enrich your app.
-    page_options = ["Recommender System","Solution Overview"]
+    page_options = ["Home", "Recommender System","Top Rated Movies", "Solution Overview", "Latest Movie News", "About Us"]
 
     # -------------------------------------------------------------------
     # ----------- !! THIS CODE MUST NOT BE ALTERED !! -------------------
@@ -53,8 +74,10 @@ def main():
     page_selection = st.sidebar.selectbox("Choose Option", page_options)
     if page_selection == "Recommender System":
         # Header contents
-        st.write('# Movie Recommender Engine')
-        st.write('### EXPLORE Data Science Academy Unsupervised Predict')
+        head, im = st.columns(2)
+        head.title('DATA LENS ANALYTICS')
+        im.image('resources/imgs/lens.jpeg', caption = 'See the Real-Time World Through our Eyes', width = 125)
+        st.write('### Movie Recommender Engine')
         st.image('resources/imgs/Image_header.png',use_column_width=True)
         # Recommender System algorithm selection
         sys = st.radio("Select an algorithm",
@@ -100,13 +123,254 @@ def main():
     # -------------------------------------------------------------------
 
     # ------------- SAFE FOR ALTERING/EXTENSION -------------------
+    if page_selection == 'Home':
+		
+		
+		#define a function to access lottiee files
+
+        def load_lottieurl(url):
+            r = requests.get(url)
+            if r.status_code != 200:
+                return None
+            return r.json()
+		
+        lottie_coding = load_lottieurl("https://lottie.host/c010cc98-6a3f-479a-a00a-78a84a9c56b5/iHcqx2032P.json")
+        phonecall_lottie = load_lottieurl("https://lottie.host/96d1924e-b132-4167-ad2a-fcbfb8918dbd/6TdAaxPO28.json")
+        
+		# header section
+        with st.container():
+                
+            st.subheader("Welcome :wave:, We are Data Lens Analytics")
+            st.image(logo_a, use_column_width=True)
+            st.write('---')
+            st.title('A Data Science Based Team Focused on Creating Real-World Data-Driven Solutions')
+            st.write(""" \n We are passionate about the use of intricately collected and analysed data to allow
+			companies and individuals to make well informed decisions""")
+		
+		#what do we do?
+        with st.container():
+            st.write('---')
+            left_column, right_column = st.columns(2)
+
+            with left_column:
+                st.header("What do we do?")
+                st.write('##')
+                st.markdown(
+					"""
+					<ul> We create highly trained AI models to clients to increase productivity and overall user experience.
+					 <li>  Leveraging available data to analyse trends and usage to be later used in recommendation engines. </li>
+					 <li>  Building recommender engines to recommend products and services to users based on well researched data. </li>
+                     <li>  Building accurate classification and regression models in relation to current technological standards. </li>
+					 <li>  Developing ready to use web-applications for solution deployment. </li>
+                     </ul>
+					    """
+				, unsafe_allow_html= True)
+            with right_column:
+                st_lottie(lottie_coding, height = 300, key = "coding" )
+			
+		# This project
+        with st.container():
+            st.write("---")
+            st.header("This Solution")
+            st.write("##")
+
+            image_column, text_column = st.columns((1,2))
+
+            with image_column:
+			# import the image
+                st.image(movie_image)
+            with text_column:
+                st.subheader("Generate movie predictions on our web application in a few steps")
+                st.markdown(
+					"""
+					<ul> 
+					<li>  Pick your favourite movies from a list.
+                    <li>  Select a prefered algorithm between a Content or Collaborative based one.
+                    <li>  Click on Recommend.
+                    <li>  Watch modern magic at work.
+                    </ul>
+				""", unsafe_allow_html= True)
+			
+            with st.container():
+                st.write('---')
+                st.header("Get In Touch With Us")
+                st.write("We will get back to you as soon as possible")
+                st.write("##")
+                contact_form = """
+				<form action="https://formsubmit.co/markasavuxx@yahoo.com" method="POST">
+     <input type="text" name="message" placeholder = "enter a message" required>
+     <input type="email" name="email" placeholder = "enter your email" required>
+     <button type="submit">Send</button>
+</form>
+					"""
+                info_column, phonecall_column = st.columns((2,1))
+
+                with info_column:
+                    st.markdown(contact_form, unsafe_allow_html=True)   
+                
+                
+                with phonecall_column:
+                    st_lottie(phonecall_lottie)
+
+				#styling the contact form
+            
+            def locall_css(filename):
+                with open(filename) as f:
+                    st.markdown(f"<style>{f.read()}</style", unsafe_allow_html=True)
+					
+                locall_css("style/style.css")    
+    
+    
+    if page_selection == "Top Rated Movies":
+        # Header Contents
+        st.write("# Top Rated Movies")
+        images = ['resources/imgs/info.webp']
+        for i in images:
+            st.image(i, use_column_width=True)
+        filters = ["None", "Top rated Movies"]
+        filter_selection = st.selectbox("Fact Check", filters)
+        if filter_selection == "Top rated Movies":
+            movie_list = pd.read_csv('resources/data/movies.csv')
+            ratings = pd.read_csv('resources/data/ratings.csv')
+            df = pd.merge(movie_list, ratings, on='movieId', how='left')
+            movie_ratings = pd.DataFrame(df.groupby('title')['rating'].mean())
+            movie_ratings["Number_Of_Ratings"] = pd.DataFrame(df.groupby('title')['rating'].count())
+            indes = movie_ratings.index
+            new_list = []
+            for movie in indes:
+                i = ' '.join(movie.split(' ')[-1])
+                new_list.append(i)
+            new_lists = []
+            for i in new_list:
+                if len(i) < 2:
+                    empty = i
+                    new_lists.append(empty)
+                elif i[0] == "(" and i[-1] == ")" and len(i) == 11:
+                    R_strip = i.rstrip(i[-1])
+                    L_strip = R_strip.lstrip(R_strip[0])
+                    spaces = ''.join(L_strip.split())
+                    data_type_int = int(spaces)
+                    new_lists.append(data_type_int)
+                else:
+                    new_lists.append(i)
+            cnn = []
+            for i in new_lists:
+                if type(i) != int:
+                    i = 0
+                    cnn.append(i)
+                else:
+                    cnn.append(i)
+            movie_ratings["Year"] = cnn
+
+            def user_interaction(Year, n):
+                list_movies = movie_ratings[movie_ratings['Year'] == Year].sort_values('Number_Of_Ratings',
+                                                                                       ascending=False).index
+                return list_movies[:n]
+
+            selected_year = st.selectbox("Year released", range(1970, 2020))
+            no_of_outputs = st.radio("Movies to view", (5, 10, 20, 50))
+            output_list = user_interaction(selected_year, no_of_outputs)
+            new_list = []
+            for movie in output_list:
+                updated_line = ' '.join(movie.split(' ')[:-1])
+                updated_line = "+".join(updated_line.split())
+                new_list.append(updated_line)
+            url = "https://www.imdb.com/search/title/?title="
+            movie_links = []
+            for i in new_list:
+                links = url + i
+                movie_links.append(links)
+            dict_from_list = dict(zip(output_list, movie_links))
+            for items in dict_from_list:
+                st.subheader(items)
+                
+
+                
     if page_selection == "Solution Overview":
         st.title("Solution Overview")
         st.write("Describe your winning approach on this page")
 
     # You may want to add more sections here for aspects such as an EDA,
     # or to provide your business pitch.
+    
+    if page_selection == "Latest Movie News":
+        st.title("Get The Latest Movie News")
+        st.write('---')
+		
+        st.write("""Stay updated on matters relating to movie releases, actors,
+        awards, financing. Never miss an update on upcoming movies and ticket releas dates to
+        be the first on at the big screen. Know about your favourite films and movie stars with single click.
+
+		"""
+		)
+        st.write('##')
+        st.image("resources/imgs/news_img.webp", width=600, caption=" Source: https://www.freepik.com/")
+        st.write('---')
+        st.write("""
+		Click the button below to to get a round up of the latest news in Hollywood from around the web.
+		 You can proceed to the news source by clicking the provided link to the article
+		""")
+        btn = st.button("Click to get latest movies related news")
+
+        if btn:
+            url ="https://newsapi.org/v2/everything?" 
+            request_params = {
+		    	"q": 'hollywood OR upcomming movies OR new movies OR hollywood actors',
+				"sort by": "latest",
+				"language": 'en',
+				"apikey": "950fae5906d4465cb25932f4c5e1202c"
+			}
+            r = requests.get(url, request_params)
+            r = r.json()
+            articles = r['articles']
+
+            for article in articles:
+                st.header(article['title'])
+                if article['author']:
+                    st.write(f"Author: {article['author']}")
+                st.write(f"Source: {article['source']['name']}")
+                st.write(article['description'])
+                st.write(f"link to article: {article['url']}")
+                #st.image(article['urlToImage'])
+                
+    
+    if page_selection == "About Us":
+        st.title("About Us")
+        st.write("We are a team of Data Scientists and Engineers passionate about building efficient Machine Learning Models")
+        st.write("Our goal is to provide accurate movie recommendations so as to provide the ultimate user experience")
+        
+        st.header("The Team")
+        
+        #create space for images and their descriptions
+        col1, col2, col3 = st.columns(3)
+        des1, des2, des3 = st.columns(3)
+        col4, col5 = st.columns(2)
+        des4, des5 = st.columns(2)
+        
+        col1.image('resources/imgs/Obinna.jpg', caption = "Data Engineer", width = 200)
+        col2.image('resources/imgs/Mark.jpg', caption = "Data Scientist", width = 200)
+        col3.image('resources/imgs/Salami.jpg', caption = "Data Scientist", width = 200)
+        
+        des1.subheader("Obinna Ekesi")
+        des1.write("Obinna is our steadfast team leader and experienced data scientist. He has a strong background in Data analytics and Project Management.")
 
+        des2.subheader("Mark Kasavuli")
+        des2.write("Mark is an experienced data scientist and app developer. He has a strong background in Data science and Front-End App Development.")
+        
+        des3.subheader("Oluwaseyi Olanike Rachael")
+        des3.write("Oluwaseyi is an experienced Project Coordinator and Data Enginner. She has background knowledge in Project Control and Data analytics.")
 
+        col4.image('resources/imgs/Musa.jpg', caption = "Data Engineer", width = 200)
+        col5.image('resources/imgs/Richard.jpg', caption = 'Data Scientist', width = 200)
+        
+        des4.subheader("Musa Aliu")
+        des4.write("Musa is an experienced Data Engineer and pipeline developer. He has vast experience with Exploratory Data Analysis.")
+        
+        des5.subheader("Richard Sam")
+        des5.write("Richard is an experienced Data Scientist. He as a strong background in Machine Learning Model Development and Deployment.")
+        
+        
+        
+        
 if __name__ == '__main__':
     main()
diff --git a/recommenders/collaborative_based.py b/recommenders/collaborative_based.py
index 861b5d8f..d4e46590 100644
--- a/recommenders/collaborative_based.py
+++ b/recommenders/collaborative_based.py
@@ -31,7 +31,10 @@
 import pandas as pd
 import numpy as np
 import pickle
+import bz2
+import os
 import copy
+import surprise
 from surprise import Reader, Dataset
 from surprise import SVD, NormalPredictor, BaselineOnly, KNNBasic, NMF
 from sklearn.metrics.pairwise import cosine_similarity
@@ -43,7 +46,9 @@
 ratings_df.drop(['timestamp'], axis=1,inplace=True)
 
 # We make use of an SVD model trained on a subset of the MovieLens 10k dataset.
-model=pickle.load(open('resources/models/SVD.pkl', 'rb'))
+ifile = bz2.BZ2File("resources/models/svd_plus_compress", "rb")
+model=pickle.load(ifile)
+ifile.close()
 
 def prediction_item(item_id):
     """Map a given favourite movie to users within the
@@ -100,6 +105,7 @@ def pred_movies(movie_list):
 
 # !! DO NOT CHANGE THIS FUNCTION SIGNATURE !!
 # You are, however, encouraged to change its content.  
+
 def collab_model(movie_list,top_n=10):
     """Performs Collaborative filtering based upon a list of movies supplied
        by the app user.
@@ -118,31 +124,108 @@ def collab_model(movie_list,top_n=10):
 
     """
 
-    indices = pd.Series(movies_df['title'])
-    movie_ids = pred_movies(movie_list)
-    df_init_users = ratings_df[ratings_df['userId']==movie_ids[0]]
-    for i in movie_ids :
-        df_init_users=df_init_users.append(ratings_df[ratings_df['userId']==i])
-    # Getting the cosine similarity matrix
-    cosine_sim = cosine_similarity(np.array(df_init_users), np.array(df_init_users))
-    idx_1 = indices[indices == movie_list[0]].index[0]
-    idx_2 = indices[indices == movie_list[1]].index[0]
-    idx_3 = indices[indices == movie_list[2]].index[0]
-    # Creating a Series with the similarity scores in descending order
-    rank_1 = cosine_sim[idx_1]
-    rank_2 = cosine_sim[idx_2]
-    rank_3 = cosine_sim[idx_3]
-    # Calculating the scores
-    score_series_1 = pd.Series(rank_1).sort_values(ascending = False)
-    score_series_2 = pd.Series(rank_2).sort_values(ascending = False)
-    score_series_3 = pd.Series(rank_3).sort_values(ascending = False)
-     # Appending the names of movies
-    listings = score_series_1.append(score_series_1).append(score_series_3).sort_values(ascending = False)
-    recommended_movies = []
-    # Choose top 50
-    top_50_indexes = list(listings.iloc[1:50].index)
-    # Removing chosen movies
-    top_indexes = np.setdiff1d(top_50_indexes,[idx_1,idx_2,idx_3])
-    for i in top_indexes[:top_n]:
-        recommended_movies.append(list(movies_df['title'])[i])
+    # Store the id of users
+    id_store=[]
+    
+    #Store movie_ids
+    mov_ids = []
+    
+    #iterate over the movie list
+    for movie in movie_list:
+        
+        #append the id from the movies_df to the list
+        mov_ids.append(int(movies_df['movieId'][movies_df['title']==movie]))
+    # For each movie selected by a user of the app,
+    # predict a corresponding user within the dataset with the highest rating
+    for i in mov_ids:
+        predictions = prediction_item(item_id = i)
+        predictions.sort(key=lambda x: x.est, reverse=True)
+        # Take the top 10 user id's from each movie with highest rankings
+        for pred in predictions[:10]:
+            id_store.append(pred.uid)
+    
+    return id_store
+
+# !! DO NOT CHANGE THIS FUNCTION SIGNATURE !!
+# You are, however, encouraged to change its content.  
+def collab_model(movie_list,top_n=10):
+    """Performs Collaborative filtering based upon a list of movies supplied
+       by the app user.
+    Parameters
+    ----------
+    movie_list : list (str)
+        Favorite movies chosen by the app user.
+    top_n : type
+        Number of top recommendations to return to the user.
+    Returns
+    -------
+    list (str)
+        Titles of the top-n movie recommendations to the user.
+    """
+
+    #store the movie ids
+    mov_ids = []
+    
+    #iterate over the movie list
+    for movie in movie_list:
+        #append the movie id from the movies_df to the list
+        mov_ids.append(int(movies_df['movieId'][movies_df['title']==movie]))
+    
+    #store predicted similar users
+    user_ids = pred_movies(movie_list)
+    
+    #generate a df with the ratings of similar users
+    df_init_users = ratings_df[ratings_df['userId'].isin(user_ids)]
+    #merge the df to obtain the movie titles
+    df_init_users = pd.merge(df_init_users, movies_df, on="movieId", how="inner")
+    #drop the genres column
+    df_init_users.drop('genres', inplace = True, axis = 1)
+    
+    #create dictionary to create a new user with the ratings
+    user_row1 = {'userId':500000, 'movieId': mov_ids[0], 'title': movie_list[0], 'rating': 5.0}
+    user_row2 = {'userId':500000, 'movieId': mov_ids[1], 'title': movie_list[1], 'rating': 5.0}
+    user_row3 = {'userId':500000, 'movieId': mov_ids[2], 'title': movie_list[2], 'rating': 5.0}
+    #append the new ratings as observations
+    df_init_users = df_init_users.append([user_row1,
+                                          user_row2, 
+                                          user_row3],
+                                        ignore_index =True)
+    
+    
+    #pivot the similar users to have unique rows
+    user_pivot = pd.pivot_table(df_init_users,
+                                values = 'rating',
+                                columns = 'title',
+                                index = 'userId')
+    
+    #fill the nulls with 0
+    user_pivot = user_pivot.fillna(0)
+    #obtain the correlation matrix
+    corr_movie_df = user_pivot.corr(method = 'pearson')
+    
+    #create a new dataframe
+    movie_sim_df = pd.DataFrame()
+    #iterate over the movie list
+    for movie in movie_list:
+        #calculate the similarity score
+        high_score = corr_movie_df[movie] * 5
+        #sort the value with the highest score at the top
+        high_score = high_score.sort_values(ascending = False)
+        #append the sorted scores to the dataframe
+        movie_sim_df = movie_sim_df.append(high_score, 
+                                          ignore_index = True)
+    
+    #store the movie titles recommended
+    all_movies_recommended = []
+    
+    #calculate the cumulative score for each movie in the df
+    for mov in movie_sim_df.sum().sort_values(ascending = False).index:
+        if mov in movie_list:
+            pass
+        else:
+            #append the movie title on the list
+            all_movies_recommended.append(mov)
+    #get the top n movies
+    recommended_movies = all_movies_recommended[:top_n]
+    #return the recommended movies
     return recommended_movies
diff --git a/recommenders/content_based.py b/recommenders/content_based.py
index ed7df363..f79571af 100644
--- a/recommenders/content_based.py
+++ b/recommenders/content_based.py
@@ -33,31 +33,31 @@
 import numpy as np
 from sklearn.metrics.pairwise import cosine_similarity
 from sklearn.feature_extraction.text import CountVectorizer
+from sklearn.preprocessing import MultiLabelBinarizer
+
 
 # Importing data
 movies = pd.read_csv('resources/data/movies.csv', sep = ',')
 ratings = pd.read_csv('resources/data/ratings.csv')
 movies.dropna(inplace=True)
 
-def data_preprocessing(subset_size):
-    """Prepare data for use within Content filtering algorithm.
-
+def data_preprocessing(data):
+    """ Preprocess data for use within for content-based filtering algorithm.
     Parameters
     ----------
     subset_size : int
         Number of movies to use within the algorithm.
-
     Returns
     -------
     Pandas Dataframe
         Subset of movies selected for content-based filtering.
-
     """
-    # Split genre data into individual words.
-    movies['keyWords'] = movies['genres'].str.replace('|', ' ')
-    # Subset of the data
-    movies_subset = movies[:subset_size]
-    return movies_subset
+    movies = data.copy()
+    # Separate genre using a ',' instead of '|'.
+    movies['bag_of_words'] = movies['genres'].str.replace('|', ' ')
+
+    movies['genres'] = movies['genres'].apply(str).apply(lambda x: x.split('|'))
+    return movies
 
 # !! DO NOT CHANGE THIS FUNCTION SIGNATURE !!
 # You are, however, encouraged to change its content.  
@@ -78,35 +78,35 @@ def content_model(movie_list,top_n=10):
         Titles of the top-n movie recommendations to the user.
 
     """
-    # Initializing the empty list of recommended movies
-    recommended_movies = []
-    data = data_preprocessing(27000)
-    # Instantiating and generating the count matrix
-    count_vec = CountVectorizer()
-    count_matrix = count_vec.fit_transform(data['keyWords'])
-    indices = pd.Series(data['title'])
-    cosine_sim = cosine_similarity(count_matrix, count_matrix)
-    # Getting the index of the movie that matches the title
-    idx_1 = indices[indices == movie_list[0]].index[0]
-    idx_2 = indices[indices == movie_list[1]].index[0]
-    idx_3 = indices[indices == movie_list[2]].index[0]
-    # Creating a Series with the similarity scores in descending order
-    rank_1 = cosine_sim[idx_1]
-    rank_2 = cosine_sim[idx_2]
-    rank_3 = cosine_sim[idx_3]
-    # Calculating the scores
-    score_series_1 = pd.Series(rank_1).sort_values(ascending = False)
-    score_series_2 = pd.Series(rank_2).sort_values(ascending = False)
-    score_series_3 = pd.Series(rank_3).sort_values(ascending = False)
-    # Getting the indexes of the 10 most similar movies
-    listings = score_series_1.append(score_series_1).append(score_series_3).sort_values(ascending = False)
-
-    # Store movie names
-    recommended_movies = []
-    # Appending the names of movies
-    top_50_indexes = list(listings.iloc[1:50].index)
-    # Removing chosen movies
-    top_indexes = np.setdiff1d(top_50_indexes,[idx_1,idx_2,idx_3])
-    for i in top_indexes[:top_n]:
-        recommended_movies.append(list(movies['title'])[i])
-    return recommended_movies
+    
+    movies_df = data_preprocessing(movies)
+    genre_list = []
+    for i in movie_list:
+        genre_list.append(list(movies_df[movies_df['title']==i]['genres'])[0])
+
+
+
+    #instantiate the multilabelbinarizer for sparsity
+    mlb =  MultiLabelBinarizer()
+    mlb.fit_transform(genre_list)
+    genre_list = mlb.classes_
+    movies_df = movies_df[~movies_df['title'].isin(movie_list)] # remove selected movies
+    movie_genre = movies_df
+
+    #looping over genres for similarity
+    for i in genre_list:
+
+        movie_genre = movie_genre[movie_genre['bag_of_words'].str.contains(i)]
+
+        if len(movie_genre) <= top_n:
+
+            break
+
+        movie_genre_2 = movie_genre
+
+
+    movie_rating = ratings[ratings['movieId'].isin(movie_genre_2['movieId'].values)][['movieId', 'rating']]
+
+    top_movies = (movie_rating.groupby(['movieId']).mean().reset_index()).sort_values('rating', ascending =False)[:top_n]
+
+    return list((movies_df[movies_df['movieId'].isin(top_movies['movieId'].values)]['title']).values)
diff --git a/resources/imgs/Mark.jpg b/resources/imgs/Mark.jpg
new file mode 100644
index 00000000..8f405c9b
Binary files /dev/null and b/resources/imgs/Mark.jpg differ
diff --git a/resources/imgs/Musa.jpg b/resources/imgs/Musa.jpg
new file mode 100644
index 00000000..2f5f24d6
Binary files /dev/null and b/resources/imgs/Musa.jpg differ
diff --git a/resources/imgs/Obinna.jpg b/resources/imgs/Obinna.jpg
new file mode 100644
index 00000000..d63a390a
Binary files /dev/null and b/resources/imgs/Obinna.jpg differ
diff --git a/resources/imgs/Richard.jpg b/resources/imgs/Richard.jpg
new file mode 100644
index 00000000..2fba5cdd
Binary files /dev/null and b/resources/imgs/Richard.jpg differ
diff --git a/resources/imgs/Salami.jpg b/resources/imgs/Salami.jpg
new file mode 100644
index 00000000..4b3d1ecc
Binary files /dev/null and b/resources/imgs/Salami.jpg differ
diff --git a/resources/imgs/info.webp b/resources/imgs/info.webp
new file mode 100644
index 00000000..a01d9f53
Binary files /dev/null and b/resources/imgs/info.webp differ
diff --git a/resources/imgs/lens.jpeg b/resources/imgs/lens.jpeg
new file mode 100644
index 00000000..f1f27147
Binary files /dev/null and b/resources/imgs/lens.jpeg differ
diff --git a/resources/imgs/movies_AI.webp b/resources/imgs/movies_AI.webp
new file mode 100644
index 00000000..65e99fe2
Binary files /dev/null and b/resources/imgs/movies_AI.webp differ
diff --git a/resources/imgs/news_img.webp b/resources/imgs/news_img.webp
new file mode 100644
index 00000000..efdbf1b9
Binary files /dev/null and b/resources/imgs/news_img.webp differ
diff --git a/resources/models/svd_plus_compress b/resources/models/svd_plus_compress
new file mode 100644
index 00000000..c90a536d
Binary files /dev/null and b/resources/models/svd_plus_compress differ
diff --git a/resources/models/tuned_svd.pkl b/resources/models/tuned_svd.pkl
new file mode 100644
index 00000000..c2484a93
Binary files /dev/null and b/resources/models/tuned_svd.pkl differ