a. Create matrix pivot

Create matrix pivot where the vertical value is users name, horizontal value is product name, and the value inside matrix is rating given by users.

matrix_pivot = pd.pivot_table(data,values='rating',index='reviewer',columns='product').fillna(0)
matrix_pivot.head()

#> product       0,2 mm Therapy Air Mask Sheet  ...  “B” oil
#> reviewer                                     ...         
#> 01lely                                  0.0  ...      0.0
#> 01putrisalma                            0.0  ...      0.0
#> 01sary                                  0.0  ...      0.0
#> 123hayoapa                              0.0  ...      0.0
#> 15ayusafitri                            0.0  ...      0.0
#> 
#> [5 rows x 3297 columns]

b. Normalize rating values

Why we do need to normalize the rating?
Because it starts with the fact that people rate often on very different scales. Say that Kiki and Satsuki use a product B, and Kiki gives rating value 5 on that product, because Satsuki has a high standart she only gives 3 on that product. Here is, the 5 from Kiki is 3 from Satsuki. To make the model better is, we can increase the efficiency of this algorithm if we normalize user’s rating by substract rating value given by user in each product with mean rating in each product.

matrix_pivot_ = matrix_pivot.values
user_ratings_mean = np.mean(matrix_pivot_, axis = 1)
user_rating = matrix_pivot_ - user_ratings_mean.reshape(-1,1)

c. Singular Value Decomposition (SVD)

Create matrix U and Vt using library scipy.

from scipy.sparse.linalg import svds
U, sigma, Vt = svds(user_rating, k = 50)

sigma = np.diag(sigma)

d. Create predictive rating

After we get the value from decomposition matrix above, we can create product ratings predictions for every user.

all_user_predicted_ratings = np.dot(np.dot(U, sigma), Vt) + user_ratings_mean.reshape(-1, 1)

And, here below matrix is result of predictive rating from each user in each product.

preds_df = pd.DataFrame(all_user_predicted_ratings, columns = matrix_pivot.columns, index=matrix_pivot.index)
preds_df

#> product       0,2 mm Therapy Air Mask Sheet  ...       “B” oil
#> reviewer                                     ...              
#> 01lely                            -0.033156  ... -4.931434e-03
#> 01putrisalma                       0.010625  ...  7.925640e-04
#> 01sary                             0.001551  ... -1.701105e-03
#> 123hayoapa                         0.015527  ...  5.204980e-07
#> 15ayusafitri                       0.003480  ...  1.148843e-03
#> ...                                     ...  ...           ...
#> zvnazole                          -0.005587  ...  3.074178e-03
#> zyshalu                           -0.013294  ...  2.718208e-04
#> zzarahs                           -0.003167  ...  4.559316e-03
#> zzfatimah                          0.002338  ...  1.161053e-02
#> zzulia                            -0.010500  ... -1.232599e-03
#> 
#> [22359 rows x 3297 columns]

e. Create recommendation

In this final step we will create recommendation product. I’ll return the product with the 5 highest predicted rating that the user hasn’t already rated.

def recommend_product(predictions_df, user, data_, num_recommendations):
   
    user_row_number = user
    sorted_user_predictions = preds_df.loc[user_row_number].sort_values(ascending=False)

    user_data = data_[data_.reviewer == (user)]
    user_full = user_data

    print('User {0} has already rated {1} product'.format(user, user_full.shape[0]))

    a = data.drop_duplicates(subset='product', keep='last')
    recommendations = (a[~a['product'].isin(user_full['product'])].
         merge(pd.DataFrame(sorted_user_predictions).reset_index(), how = 'left',
               left_on = 'product',
               right_on = 'product').
         rename(columns = {user_row_number: 'Predictions'}).
         sort_values('Predictions', ascending = False).
                       iloc[:num_recommendations, :-1]
                      )

    return user_full, recommendations

Input the user id to whom you want recommend the product.

user = 'zzulia'
already_rated, predictions = recommend_product(preds_df, user, data,5)

#> User zzulia has already rated 3 product

Result below shown that “zzulia” already rate 3 product. Twice for Facial Mask with different rating in each product, and once for Pembersih Two In One Bengkoang Whitening.

already_rated

#>        reviewer  rating                                   product
#> 70013    zzulia       3                               Facial Mask
#> 88179    zzulia       2                               Facial Mask
#> 115840   zzulia       5  Pembersih Two In One Bengkoang Whitening

And, here below 5 highest predicted rating from user id “zzulia”. The recommendation system suggest “zzulia” to buy Prominent Essence Facial Mask, Facial Mask Bedak Dingin, Oil Control Mask, White Aqua Serum Sheet Mask, and Essential Vitamin. Suggested products are dominated with “Mask” product, because from historical data above “zzulia” already rate 2 product with category "Mask.

prod_pred = predictions['product']

prod_pred

#> 2040    Prominent Essence Facial Mask
#> 2225         Facial Mask Bedak Dingin
#> 1988                 Oil Control Mask
#> 2000      White Aqua Serum Sheet Mask
#> 1661                Essential Vitamin
#> Name: product, dtype: object